11.June Nashville, US / Hybrid

NTIRE 2025

New Trends in Image Restoration and Enhancement workshop

and associated challenges

in conjunction with CVPR 2025
LIVE on Zoom IMPORTANT DATES NTIRE2024 MAI2025 AIS2024 AIM2025

Join NTIRE 2025 workshop online Zoom for LIVE, talks, Q&A, interaction

No registration required for Zoom attendance.
Join NTIRE 2025 also in-person, room Davidson C3, Music City Center, Nashville.
The event starts 11.06.2025 at 9:00 CDT / 14:00 UTC / 22:00 China time.
Check the NTIRE 2025 schedule.

Sponsors

Call for papers

Image restoration, enhancement and manipulation are key computer vision tasks, aiming at the restoration of degraded image content, the filling in of missing information, or the needed transformation and/or manipulation to achieve a desired target (with respect to perceptual quality, contents, or performance of apps working on such images). Recent years have witnessed an increased interest from the vision and graphics communities in these fundamental topics of research. Not only has there been a constantly growing flow of related papers, but also substantial progress has been achieved.

Each step forward eases the use of images by people or computers for the fulfillment of further tasks, as image manipulation serves as an important frontend. Not surprisingly then, there is an ever growing range of applications in fields such as surveillance, the automotive industry, electronics, remote sensing, or medical image analysis etc. The emergence and ubiquitous use of mobile and wearable devices offer another fertile ground for additional applications and faster methods.

This workshop aims to provide an overview of the new trends and advances in those areas. Moreover, it will offer an opportunity for academic and industrial attendees to interact and explore collaborations.

This workshop builds upon the success of New Trends in Image Restoration and Enhancement (NTIRE) editions at: CVPR 2024 , 2023 , 2022 , 2021, 2020 , 2019 , 2018 and 2017 and at ACCV 2016, Advances in Image Manipulation (AIM) workshop at ECCV 2024,ECCV 2022,ICCV 2021, ECCV 2020,ICCV 2019, Mobile AI (MAI) workshop at CVPR 2024 , 2023 , 2022 , and 2021 , Vision, Graphics and AI for Streaming (AIS) workshop at CVPR 2024 , Perceptual Image Restoration and Manipulation (PIRM) workshop at ECCV 2018 , the workshop and Challenge on Learned Image Compression (CLIC) editions at CVPR 2018, CVPR 2019, CVPR 2020, CVPR 2021, CVPR 2022, DCC 2024. Moreover, it relies on the people associated with the PIRM, AIS, CLIC, MAI, AIM, and NTIRE events such as organizers, PC members, distinguished speakers, authors of published papers, challenge participants and winning teams.

Papers addressing topics related to image/video manipulation, restoration and enhancement are invited. The topics include, but are not limited to:

  • Image/video inpainting
  • Image/video deblurring
  • Image/video denoising
  • Image/video upsampling and super-resolution
  • Image/video filtering
  • Image/video de-hazing, de-raining, de-snowing, etc.
  • Demosaicing
  • Image/video compression
  • Removal of artifacts, shadows, glare and reflections, etc.
  • Image/video enhancement: brightening, color adjustment, sharpening, etc.
  • Hyperspectral image restoration, enhancement, manipulation
  • Underwater image restoration, enhancement, manipulation
  • Light field image restoration, enhancement, manipulation
  • Aerial and satellite image restoration, enhancement, manipulation
  • Methods robust to changing weather conditions / adverse outdoor conditions
  • Image/video manipulation on constrained settings/mobile devices
  • Image/video restoration and enhancement on constrained settings/mobile devices
  • Image-to-image translation
  • Video-to-video translation
  • Image/video manipulation
  • Perceptual manipulation
  • Style transfer
  • Image/video generation and hallucination
  • Image/video quality assessment
  • Image/video semantic segmentation
  • Perceptual enhancement
  • Multimodal translation
  • Depth estimation
  • Saliency and gaze estimation
  • Studies and applications of the above.

NTIRE 2025 challenges

One needs to check the corresponding competition page(s) in order to learn more about and to register to access the data and participate in the challenge(s) of interest.

Important dates



Challenges Event Date (always 23:59 PT)
Site online January 3, 2025
Release of train data and validation data January 10, 2025
Validation server online January 30, 2025
Final test data release, validation server closed March 14, 2025
Test phase submission deadline March 21, 2025
Fact sheets, code/executable submission deadline March 22, 2025
Preliminary test results release to the participants March 24, 2025
Paper submission deadline for entries from the challenges March 29, 2025 Anywhere on Earth (EXTENDED)
Workshop Event Date (always 23:59 PT)
Paper submission deadline March 17, 2025 (EXTENDED)
Regular Paper decision notification March 31, 2025
Paper submission deadline (only for methods from NTIRE 2025 challenges and papers reviewed elsewhere!) March 29, 2025 Anywhere on Earth (EXTENDED)
Challenge/Late Paper decision notification March 31, 2025
Camera ready deadline April 12, 2025
Workshop day June 11, 2025

Submit



Instructions and Policies
Format and paper length

A paper submission has to be in English, in pdf format, and at most 8 pages (excluding references) in double column. The paper format must follow the same guidelines as for all CVPR submissions.
https://cvpr.thecvf.com/Conferences/2025/AuthorGuidelines

Double-blind review policy

The review process is double blind. Authors do not know the names of the chair/reviewers of their papers. Reviewers do not know the names of the authors.

Dual submission policy

Dual submission is not allowed. If a paper is submitted also to CVPR and accepted, the paper cannot be published both at the CVPR and the workshop.

Submission site

https://cmt3.research.microsoft.com/NTIRE2025

Proceedings

Accepted and presented papers will be published after the conference in CVPR Workshops proceedings together with the CVPR2025 main conference papers.

Author Kit

https://github.com/cvpr-org/author-kit/archive/refs/tags/CVPR2025-v3.1(latex).zip
The author kit provides a LaTeX2e template for paper submissions. Please refer to the kit for detailed formatting instructions.

People



Organizers

  • Radu Timofte, University of Wurzburg,
  • Zongwei Wu, University of Wurzburg
  • Florin Vasluianu, University of Wurzburg
  • Marcos V. Conde, University of Wurzburg,
  • Egor Ershov, AIRI
  • Sergey Korchagin, AIRI
  • Nikola Banić, Gideon Brothers
  • Yingqian Wang, NUDT
  • Yulan Guo, Sun Yat-sen University
  • Pierluigi Zama Ramirez, University of Bologna
  • Luigi Di Stefano, University of Bologna
  • Nikolay Safonov, Lomonosov Moscow State University
  • Dmitry Vatolin, Lomonosov Moscow State University
  • Shuhao Han, Nankai University
  • Haotian Fan, Bytedance
  • Chongyi Li, Nankai University
  • Varun Jain, Microsoft
  • Quan Zou, Microsoft
  • Xin Li, USTC
  • Kun Yuan, Kuaishou
  • Zhibo Chen, USTC
  • Yeying Jin, National University of Singapore
  • Robby T. Tan, National University of Singapore
  • Xin Jin, Eastern Institute of Technology, Ningbo
  • Sangmin Lee, Samsung
  • Eunpil Park, Samsung
  • Hyunhee Park, Samsung
  • Kangning Yang, OPPO AI Center
  • Jie Cai, OPPO AI Center
  • Chiu Man Ho, OPPO AI Center
  • Tim Seizinger, University of Wurzburg
  • Zhuyun Zhou, CNRS - Université Bourgogne
  • Lei Sun, INSAIT
  • Andrea Alfarano, INSAIT
  • Zheng Chen, Shanghai Jiao Tong University
  • Jingkai Wang, Shanghai Jiao Tong University
  • Yulun Zhang, Shanghai Jiao Tong University
  • Hang Guo, Tsinghua University
  • Yawei Li, ETH Zurich
  • Xiaohong Liu, Shanghai Jiao Tong University
  • Xiongkuo Min, Shanghai Jiao Tong University
  • Qiang Hu, Shanghai Jiao Tong University
  • Jie Liang, OPPO Research Institute
  • Qiaosi Yi, The Hong Kong Polytechnic University
  • Bin Ren, University of Trento
  • Shuhang Gu, UESTC
  • Marcos Conde, University of Wurzburg
  • Yuqian Fu, INSAIT
  • Xingyu Qiu, Fudan University
  • Nicu Sebe, University of Trento
  • Ming-Hsuan Yang, University of California at Merced & Google
  • Nancy Mehta, University of Wurzburg
  • Kai Zhang, Nanjing University
  • Kyoung Mu Lee, Seoul National University
  • Lei Zhang, The Hong Kong Polytechnic University, The OPPO Research Institute
  • Luc Van Gool, INSAIT & KU Leuven & ETH Zurich,




PC Members (TBU)

  • Mahmoud Afifi, Google
  • Timo Aila, NVIDIA
  • Codruta Ancuti, UPT
  • Boaz Arad, Ben-Gurion University of the Negev
  • Siavash Arjomand Bigdeli, DTU
  • Michael S. Brown, York University / Samsung AI Center
  • Chia-Ming Cheng, MediaTek
  • Sunghyun Cho, Samsung
  • Marcos V. Conde, University of Wurzburg
  • Chao Dong, SIAT
  • Touradj Ebrahimi, EPFL
  • Michael Elad, Technion
  • Paolo Favaro, University of Bern
  • Corneliu Florea, University Politechnica of Bucharest
  • Alessandro Foi, Tampere University of Technology
  • Peter Gehler, Amazon
  • Bastian Goldluecke, University of Konstanz
  • Jinjin Gu, University of Sydney
  • Shuhang Gu, UEST
  • Christine Guillemot, INRIA
  • Chiu Man Ho, OPPO,
  • Hiroto Honda, GO Inc.
  • Andrey Ignatov, ETH Zurich
  • Eddy Ilg, University of Technology Nuremberg
  • Michal Irani, Weizmann Institute, Israel
  • Christian Ledig, University of Bamberg
  • Seungyong Lee, POSTECH
  • Kyoung Mu Lee, Seoul National University
  • Yawei Li, ETH Zurich
  • Stephen Lin, Microsoft Research
  • Chen Change Loy, Chinese University of Hong Kong
  • Vladimir Lukin, National Aerospace University, Ukraine
  • Vasile Manta, Technical University of Iasi
  • Rafal Mantiuk, University of Cambridge
  • Zibo Meng, OPPO
  • Yusuke Monno, Tokyo Institute of Technology
  • Vinay P. Namboodiri, University of Bath/li>
  • Sylvain Paris, Adobe
  • Rakesh Ranjan, Meta Reality Labs
  • Wenqi Ren, Sun Yat-Sen University
  • Stefan Roth, TU Darmstadt
  • Aline Roumy, INRIA
  • Yoichi Sato, University of Tokyo
  • Nicu Sebe, University of Trento
  • Eli Shechtman, Creative Intelligence Lab at Adobe Research
  • Gregory Slabaugh, Queen Mary University of London
  • Sabine Süsstrunk, EPFL
  • Masayuki Tanaka, Tokyo Institute of Technology
  • Hao Tang, ETH Zurich
  • Jean-Philippe Tarel, G. Eiffel University
  • Qi Tian, Huawei Cloud & AI
  • Radu Timofte, University of Wurzburg
  • George Toderici, Google
  • Luc Van Gool, INSAIT, ETH Zurich, KU Leuven
  • Javier Vazquez-Coral, Autonomous University of Barcelona
  • Longguang Wang, NUDT
  • Yingqian Wang, NUDT
  • Xintao Wang, Tencent
  • Gordon Wetzstein, Stanford University
  • Ming-Hsuan Yang, University of California at Merced & Google
  • Ren Yang, Microsoft Research
  • Kai Zhang, Nanjing University
  • Yulun Zhang, Shanghai Jiao Tong University
  • Jun-Yan Zhu, Carnegie Mellon University
  • Wangmeng Zuo, Harbin Institute of Technology

Invited Talks (TBU)



Torsten Sattler

CTU Prague

Title: 3D Reconstruction with Gaussian Splatting

Abstract: Accurate 3D reconstruction is a core computer vision problem with many applications, including autonomous robots such as self-driving cars, cultural heritage documentation, and content creation for the entertainment industry (movies, games, etc.). Traditionally, 3D reconstructions have been based on 3D meshes and point clouds. Recently, learning-based approaches, such as neural radiance fields (NeRFs) and most recently 3D Gaussian Splatting (3DGS), have become popular. These representations are learned from images with known intrinsics and extrinsics and generate (close-to) photorealistic representations of scenes and objects. Compared to NeRFs, which can be slow to train and slow to render, 3DGS offers both faster training and test times. This talk first briefly reviews the original 3DGS formulation before identifying shortcomings and explaining how to resolve them. In particular, we will discuss (i) how to handle artifacts in the reconstruction caused by a limited set of training viewpoints, (ii) how to extend the original formulation for handling images taken under different conditions (day, night, etc.), and (iii) how to extract accurate 3D meshes from 3DGS representations by defining a field on top of the 3D Gaussians used to represent the scene. In addition, we will briefly mention ongoing efforts to ensure that benchmark results are comparable and that comparisons are fair.

Bio: Torsten Sattler is a Senior Researcher at CTU. Before, he was a tenured associate professor at Chalmers University of Technology. He received a PhD in Computer Science from RWTH Aachen University, Germany, in 2014. From Dec. 2013 to Dec. 2018, he was a post-doctoral and senior researcher at ETH Zurich. Torsten's research interests include visual localization, local feature extraction and matching, camera geometry estimation, 3D reconstruction, neural scene representations and neural rendering, and semantic scene understanding. Torsten has contributed popular benchmarks on long-term visual localization and multi-view stereo. In general, Torsten is interested in finding suitable scene representations for 3D computer vision tasks. He regularly reviews or is an area chair for the main computer vision conferences (CVPR, ECCV, ICCV). He was / is an associate editor for IEEE RA-L and IEEE TPAMI, has been a program chair for DAGM GCPR 2020 and ECCV 2024, and a general chair for 3DV 2022. Torsten is an ELLIS Fellow, a member of the ELLIS PhD and Postdoc Program Committee, and will be a member of the next ELLIS board.

Lu Jiang

TikTok

Title: Cost-Effective Training of Video Generation Foundation Model

Abstract: Video generation requires significant resources for both training and inference. In this talk, I will share lessons learned in developing a cost-efficient strategy for training and serving a video generation foundation model. We emphasize key design choices that enable strong performance under limited computational constraints. Specifically, we will study Seaweed-7B (https://seaweed.video/), a mid-sized model that delivers results comparable to, or even surpassing, those of much larger models trained with substantially more GPU resources. We also briefly discuss how to extend the model’s capabilities to downstream applications such as human generation, long-form video storytelling, and real-time video generation.

Bio: Lu Jiang is currently a research lead at ByteDance USA, leading foundation models for video generation. He is a former adjunct faculty member at Carnegie Mellon University and a research scientist and manager at Google. His research has been integral in multiple products, such as YouTube, Google Cloud, Google Ads, Waymo, TikTok, and CapCut, impacting the daily lives of billions of users worldwide. His research interests lie in the interdisciplinary field of Multimedia and Machine Learning, with a focus on video creation and multimodal foundation models. His work has been awarded the Best Paper at top machine learning venues such as ICML and IJCAI-JAIR, and has also been nominated for the Best Paper at ACL and CVPR. Lu is an active member of the research community, serving as an AI panelist for America's Seed Fund (NSF SBIR). He regularly acts as an area chair for conferences like CVPR, ICCV, ICML, ICLR, NeurIPS, and as an associate editor for CVIU, IEEE TPAMI, and TMLR.

Jia-Bin Huang

University of Maryland

Title: Modeling and Editing Associated Effects

Abstract: Rich visual phenomena—such as soft shadows cast by objects, subtle reflections in windows, and complex interplays of light—are central to realistic scene understanding and synthesis. In this talk, we will show how explicitly modeling these visual cues allow us to reconstructing 3D scenes with complex reflections. Then we will discuss how we can leverage generative priors for editing these associated effects for intuitive visual manipulation.

Bio: Jia-Bin Huang is a Capital One-endowed Associate Professor of Computer Science at the University of Maryland College Park. Before coming to UMD, Huang was a research scientist at Meta Reality Labs. Before that, he was an Assistant Professor of Electrical and Computer Engineering at Virginia Tech. Huang received his Ph.D. from the University of Illinois, Urbana-Champaign (UIUC) in 2016. His research interests include 3D computer vision, generative models, and computational photography. Huang is the recipient of the Thomas & Margaret Huang Award, NSF CRII award, faculty award from Samsung, Google, 3M, Qualcomm, and a Google Research Scholar Award.

Schedule (TBU)

Join NTIRE 2025 Zoom meeting for LIVE, talks, Q&A, interaction.
No registration required for Zoom attendance.
Join NTIRE 2025 also in-person, room Davidson C3, Music City Center, Nashville.

All the accepted NTIRE workshop papers have in-person poster presentation June 11. A subset of the accepted NTIRE workshop papers have also oral presentation. All the accepted NTIRE workshop papers are published under the book title "2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops" by

Computer Vision Foundation Open Access and IEEE Xplore Digital Library



papers (pdf, suppl. mat) will be available at https://openaccess.thecvf.com/CVPR2025_workshops/NTIRE


[14:00 UTC] 09:00
"NTIRE 2025: 10th Edition Overview and Awards"
Zongwei Wu ( University of Wurzburg )
 [slides]
[14:05 UTC] 09:05
Challenge Report:"Image Shadow Removal"
Florin-Alexandru Vasluianu et al.
[14:05 UTC] 09:05 NTIRE 2025 Image Shadow Removal Challenge Report
Florin-Alexandru Vasluianu (University of Würzburg); Tim Seizinger (University of Würzburg); Zhuyun Zhou (CNRS - Université de Bourgogne); Cailian Chen (Shanghai Jiao Tong University); Zongwei Wu (University of Wurzburg); Radu Timofte (University of Würzburg) et al

[14:15 UTC] 09:15
Challenge Report:"HR Depth from Images of Specular and Transparent Surfaces"
Pierluigi Zama Ramirez et al.
[14:15 UTC] 09:15 NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
Pierluigi Zama Ramirez (University of Bologna)*; Fabio Tosi (University of Bologna); Luigi Di Stefano (University of Bologna); Radu Timofte (University of Wurzburg, Germany) et al

[14:25 UTC] 09:25 SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation
Mykola Lavreniuk (Space Research Institute)*; Alla Lavreniuk (National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute»)

[16:20 UTC] 09:30
Invited Talk: " 3D Reconstruction with Gaussian Splatting "
Torsten Sattler (Czech Technical University, Prague)
[slides]
[15:00 UTC] 10:00
Challenge Report:"Ambient Lighting Normalization"
Florin-Alexandru Vasluianu et al.
[15:00 UTC] 10:00 NTIRE 2025 Ambient Lighting Normalization Challenge
Florin-Alexandru Vasluianu (Computer Vision Lab, University of Wurzburg)*; Tim Seizinger (Computer Vision Lab, University of Wurzburg); Zhuyun Zhou (CNRS - Université de Bourgogne); Zongwei Wu (Computer Vision Lab, University of Wurzburg); Radu Timofte (Computer Vision Lab, University of Wurzburg) et al

[15:10 UTC] 10:10 Frequency-Prior Enhanced Ambient Lighting Normalization via Visual Perceptual Refinement
Yuanfei Bao (University of Science and Technology of China); Xin Lu (University of Science and Technology of China); Xingbo Wang (University of Science and Technology of China); Jiarong Yang (University of Science and Technology of China); Anya Hu (University of Science and Technology of China); Kunyu Wang (University of Science and Technology of China); Jie Xiao (University of Science and Technology of China); Dong Li (University of Science and Technology of China); Xueyang Fu (University of Science and Technology of China)*; Zheng-Jun Zha (University of Science and Technology of China)

[15:15 UTC] 10:15
Challenge Report:"Real-World Face Restoration"
Zheng Chen et al.
[15:15 UTC] 10:15 NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results
Zheng Chen (Shanghai Jiao Tong University); Jingkai Wang (Shanghai Jiao Tong University); Kai Liu (Shanghai Jiao Tong University); Jue Gong (Shanghai Jiao Tong University); Lei Sun (ETH Zurich); Zongwei Wu (University of Wurzburg); Radu Timofte (University of Wurzburg); Yulun Zhang (hanghai Jiao Tong University) et al

[15:25 UTC] 10:25
Challenge Reports:"Text to Image Generation Model Quality Assessment"
Shuhao Han et al.
[15:25 UTC] 10:25 NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment
Shuhao Han (Nankai University)*; Haotian Fan (Bytedance); Fangyuan Kong (Bytedance); Wenjie Liao (Bytedance); Chunle Guo (Nankai University); Chongyi Li (Nankai University); Radu Timofte (University of Würzburg) et al.

[15:35 UTC] 10:35 Instruction-augmented Multimodal Alignment for Image-Text and Element Matching
Xinli Yue (Wuhan University); JianHui Sun (WeChat); Junda Lu (WeChat); Liangchao Yao (WeChat); FAN XIA (WeChat); Tianyi Wang (WeChat); Fengyun Rao (WeChat); JING LYU (WeChat); Yuetang Deng (WeChat) et al.

[15:40 UTC] 10:40
Challenge Report :" Short-form UGC Video Quality Assessment"
Xin Li et al.
[15:40 UTC] 10:40 NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results
Xin Li (University of Science and Technology of China)*; Kun Yuan (Kuaishou Technology); Bingchen Li (University of Science and Technology of China); Fengbin Guan (University of Science and Technology of China); Yizhen Shao (Kuaishou Technology); Zihao Yu (University of Science and Technology of China); Xijun Wang (University of Science and Technology of China); Yiting Lu (University of Science and Technology of China); Wei Luo (University of Science and Technology of China); Suhang Yao (University of Science and Technology of China); Ming Sun (Kuaishou Technology); Chao Zhou (Beijing Kuaishou Technology Co., Ltd); Zhibo Chen (University of Science and Technology of China); Radu Timofte (University of Wurzburg) et al.

[15:50 UTC] 10:50 Enhanced Semantic Extraction and Guidance for UGC Image Super Resolution
Yiwen Wang (Shanghai Jiao Tong University); Ying Liang (Shanghai Jiao Tong University)*; Yuxuan Zhang (Shanghai Jiao Tong University); Xinning Chai (Shanghai Jiao Tong University); Zhengxue Cheng (Shanghai Jiao Tong University); Yingsheng Qin (Transsion); Yucai Yang (Transsion); Rong Xie (Shanghai Jiao Tong University); Li Song (Shanghai Jiao Tong University)

[15:55 UTC] 10:55 Towards Holistic Visual Quality Assessment of AI-Generated Videos: A LLM-Based Multi-Dimensional Evaluation Model
Zelu Qi (Communication University of China)*; Shi Ping (Communication University of China); Chaoyang Zhang (Communication University of China); Shuqi Wang (Communication University of China); Fei Zhao (Communication University of China); Da Pan (Communication University of China); Zefeng Ying (Communication University of China)

[16:00 UTC] 11:00
Challenge Report :" Video Quality Enhancement for Video Conferencing"
Varun Jain et al.
[16:00 UTC] 11:00 NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and Results
Varun Jain (Microsoft)*; Zongwei Wu (University of Wurzburg); Quan Zou (Microsoft); Louis Florentin (Microsoft); Henrik Turbell (Microsoft); Sandeep Siddhartha (Microsoft); Radu Timofte (University of Wurzburg) et al.

[16:10 UTC] 11:10 Efficient Video Quality Enhancement via Look-up Tables
Huimin Zeng (Northeastern University), Qi Chen (Johns Hopkins University)

[16:15 UTC] 11:15 Q-CIDNet: Perceptual Quality aware Color and Intensity Decoupling Network for Video Quality Enhancement
Ajeet Kumar Verma (IIT Jammu), Shweta Tripathi (IIT Jammu), Vinit Jakhetiya (IIT Jammu), Badri N Subhdhi (IIT Jammu), Sunil Jaiswal (K|Lens GmbH)


[16:20 UTC] 11:20
Challenge Report :"UGC Video Enhancement"
Nickolay Safonov et al.
[16:20 UTC] 11:20 NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results
Nickolay Safonov (MSU); Alexey Bryntsev (Lomonosov Moscow State University); Andrey Moskalenko (Lomonosov Moscow State University); Dmitry Kulikov (Lomonosov Moscow State University); Dmitriy Vatolin (Lomonosov Moscow State University); Radu Timofte (University of Würzburg), et al

[16:30 UTC] 11:30
Invited Talk: " Cost-Effective Training of Video Generation Foundation Model "
Lu Jiang (TikTok)
[slides]
[17:00 UTC] 12:00
Challenge Report :" XGC Quality Assessment"
Xiaohong Liu et al.
[17:00 UTC] 12:00 NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results
Xiaohong Liu (Shanghai Jiao Tong University)*; Xiongkuo Min (Shanghai Jiao Tong University); Qiang Hu (Shanghai Jiao Tong University); Xiaoyun Zhang (Shanghai Jiao Tong University); Jie Guo (Peng Cheng Laboratory); Guangtao Zhai (Shanghai Jiao Tong University); Shushi Wang (Shanghai Jiao Tong University); Yingjie Zhou (Shanghai Jiao Tong University); Lu Liu (Shanghai Jiao Tong University); Jingxin Li (China National Information Technology Standardization Committee Multimedia Subcommittee); Liu Yang (Shanghai Jiao Tong University); Farong Wen (Shanghai Jiao Tong University); Li Xu (Peng Cheng Laboratory); Yanwei Jiang (Shanghai Jiao Tong University); Xilei Zhu (Shanghai Jiao Tong University); Chunyi Li (Shanghai Jiao Tong University); Zicheng Zhang (Shanghai Jiao Tong University); Huiyu Duan (Shanghai Jiao Tong University); Xiele Wu (Shanghai Jiao Tong University); Yixuan Gao (Shanghai Jiao Tong University); Yuqin Cao (Shanghai Jiao Tong University); Jun Jia (Shanghai Jiao Tong University); Wei Sun (Shanghai Jiao Tong University); Jiezhang Cao (Harvard University); Radu Timofte (University of Würzburg), et al

[17:10 UTC] 12:10 Multi-Dimensional Quality Assessment for UGC Videos via Modular Multi-Modal Vision-Language Models
Weixia Zhang (Shanghai Jiao Tong University)*; Bingkun Zheng (Shanghai Jiao Tong University); Junlin Chen (Shanghai Jiao Tong University); Zhihua Wang (City University of Hong Kong)

[17:15 UTC] 12:15-13:30
Lunch Break
[18:30 UTC] 13:30
Invited Talk: " Modeling and Editing Associated Effects "
Jia-Bin Huang (University of Maryland)
[slides]
[19:00 UTC] 14:00
Challenge Report:"RAW Image Reconstruction from RGB on Smartphones"
Marcos Conde et al.
[19:00 UTC] 14:00 RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report
Marcos Conde (University of Würzburg & Sony PlayStation)*; Radu Timofte (University of Würzburg) et al.

[19:10 UTC] 14:10
Challenge Report:"RAW Image Restoration and Super-Resolution"
Marcos Conde et al.
[19:10 UTC] 14:10 NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution
Marcos Conde (University of Würzburg & Sony PlayStation)*; Radu Timofte (University of Würzburg) et al.

[19:15 UTC] 14:15
Challenge Report:"Burst HDR and Restoration"
Sangmin Lee et al.
[19:20 UTC] 14:20 NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results
Sangmin Lee (Samsung Electronics MX Business - Camera Innovation Group)*; Eunpil Park (Samsung Electronics MX Business - Camera Innovation Group); Angel Canelo (Samsung Electronics MX Business - Camera Innovation Group); Hyunhee Park (Samsung Electronics MX Business - Camera Innovation Group); Youngjo Kim (Samsung Electronics MX Business - Camera Innovation Group); Hyungju Chun (Samsung Electronics MX Business - Camera Innovation Group); Xin Jin ( Nankai University); Chongyi Li (Nankai University); Chun-Le Guo (Nankai University); Radu Timofte (University of Wurzburg) et al.

[19:25 UTC] 14:25
Challenge Reports:"Efficient Super-Resolution"
Bin Ren et al.
[19:30 UTC] 14:30 The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report
Bin Ren (University of Trento); Hang Guo (Tsinghua University); Lei Sun (INSAIT); Zongwei Wu (University of Wurzburg); Radu Timofte (University of Wurzburg); Yawei Li (ETH Zürich) et al.

[19:40 UTC] 14:40 Distillation-Supervised Convolutional Low-Rank Adaptation for Efficient Image Super-Resolution
Xinning Chai (Shanghai Jiao Tong University); Yao Zhang (Shanghai Jiao Tong University)*; Yuxuan Zhang (Shanghai Jiao Tong University); Zhengxue Cheng (Shanghai Jiao Tong University); Yingsheng Qin (Transsion, China); Yucai Yang (Transsion, China); Li Song (Shanghai Jiao Tong University)

[19:45 UTC] 14:45 SPAN-F: An Enhanced Swift Parameter-free Attention Network for Efficient Super-Resolution
Hongyuan Yu (Xiaomi Inc.), Pufan Xu (Tsinghua University), Cheng Wan (Cornell University), Zhijuan Huang (Xiaomi Inc.), Peng Guo (Hanhai Information Tech. Co., Ltd), Shuyuan Cui (Huatai Insurance Group Co., Ltd),  Chenjun Li (Cornell University), Xuehai Hu, Pan Pan (Xiaomi Inc.), Xin Zhang (Xiaomi Inc.), Heng Zhang (Xiaomi Inc.)

[19:50 UTC] 14:50
Challenge Reports:"Image Super-Resolution (×4)"
Zheng Chen et al.
[19:50 UTC] 14:50 NTIRE 2025 Challenge on Image Super-Resolution (×4): Methods and Results
Zheng Chen (Shanghai Jiao Tong University)*; Kai Liu (Shanghai Jiao Tong University); Jue Gong (Shanghai Jiao Tong University); Jingkai Wang (Shanghai Jiao Tong University); Lei Sun (ETH Zurich); Zongwei Wu (University of Wurzburg); Radu Timofte (University of Wurzburg); Yulun Zhang (Shanghai Jiao Tong University) et al.

[19:55 UTC] 14:55
Challenge Reports:"Light Field Image Super-Resolution"
Yingqian Wang et al.
[20:00 UTC] 15:00 NTIRE 2025 Challenge on Light Field Image Super-Resolution: Methods and Results
Yingqian Wang (National University of Defense Technology)*; Zhengyu Liang (National University of Defense Technology ); Fengyuan Zhang (National University of Defense Technology); Lvli Tian (National University of Defense Technology); Longguang Wang (Aviation University of Air Force); Juncheng Li (Shanghai University); Jungang Yang (National University of Defense Technology); Radu Timofte (University of Würzburg); Yulan Guo (Sun Yat-sen University) et al.

[20:10 UTC] 15:10 LFTransMamba: A Hybrid Mamba-Transformer Model for Light Field Image Super-Resolution
Kai Jin (Bigo Technology Pte. Ltd.); Zeqiang Wei (Beijing University of Posts and Telecommunications); Angulia Yang (Bigo Technology Pte. Ltd.); Di Wu (Beijing University of Posts and Telecommunications); Mingzhi Gao (Bigo Technology Pte. Ltd.); Xiuzhuang Zhou (Beijing University of Posts and Telecommunications)*

[20:10 UTC] 15:10 ####### place holder, challenge runner-up
#########

[17:00 UTC] 15:15-15:30
Coffee Break
[20:30 UTC] 15:30
Challenge Report:"Low Light Image Enhancement"
Xiaoning Liu et al.
[20:30 UTC] 15:30 NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results
Xiaoning Liu (University of Electronic Science and Technology of China); Zongwei Wu (University of Wurzburg)*; Florin-Alexandru Vasluianu (University of Wurzburg); Hailong Yan (University of Electronic Science and Technology of China); Bin Ren (University of Trento); Yulun Zhang (Shanghai Jiao Tong University); Shuhang Gu (University of Electronic Science and Technology of China); Le Zhang (University of Electronic Science and Technology of China); Ce Zhu (University of Electronic Science and Technology of China); Radu Timofte (University of Wurzburg) et al.

[20:40 UTC] 15:40
Challenge Report:"Night Photography Rendering"
Egor Ershov et al.
[20:40 UTC] 15:40 NTIRE 2025 Challenge on Night Photography Rendering
Egor Ershov (AIRI); Sergey Korchagin (IITP RAS)*; Alexei Khalin (IITP RAS); Artyom Panshin (IITP RAS); Arseniy Terekhin (IITP RAS); Ekaterina Zaychenkova (IITP RAS); Georgiy Lobarev (IITP RAS); Vsevolod Plokhotnyuk (IITP RAS); Denis Abramov (IITP RAS); Elisey Zhdanov (IITP RAS); Sofia Dorogova (IITP RAS); Yasin Mamedov (IITP RAS); Nikola Baniс (Gideon Brothers); Georgii Perevozchikov (University of Wurzburg); Radu Timofte (University of Wurzburg) et al.

[20:50 UTC] 15:50
Challenge Report:"Single Image Reflection Removal in the Wild"
Kangning Yang et al.
[20:50 UTC] 15:50 NTIRE 2025 Challenge on Single Image Reflection Removal in the Wild: Datasets, Methods and Results
Kangning Yang (OPPO AI Center)*; Jie Cai (OPPO AI Center); Ling Ouyang (OPPO AI Center); Florin-Alexandru Vasluianu (University of Würzburg); Radu Timofte (University of Würzburg) et al

[21:00 UTC] 16:00 [20:55 UTC] 15:55
Challenge Report:"Restore Any Image Model (RAIM)"
Jie Liang et al.
[21:00 UTC] 16:00 NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challenge
Jie Liang (OPPO Research Institute)*; Radu Timofte (University of Wurzburg & ETH Zurich); Qiaosi Yi (The Hong Kong Polytechnic University); Zhengqiang Zhang (The Hong Kong Polytechnic University); Shuaizheng Liu (The Hong Kong Polytechnic University); Lingchen Sun (The Hong Kong Polytechnic University); Rongyuan Wu (The Hong Kong Polytechnic University); Xindong Zhang (OPPO Research Institute); Hui Zeng (OPPO Research Institute); Lei Zhang (Hong Kong Polytechnic University, Hong Kong, China) et al

[21:10 UTC] 16:10
Challenge Report:"Raindrop Removal for Dual-Focused Images"
Xin Li et al.
[21:10 UTC] 16:10 NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
Xin Li (University of Science and Technology of China)*; Yeying Jin (National University of Singapore); Xin Jin (Eastern Institute of Technology, Ningbo); Zongwei Wu (University of Würzburg); Bingchen Li (University of Science and Technology of China); Yufei Wang (Snap Research); Wenhan Yang (Pengcheng Laboratory); Yu Li (IDEA); Zhibo Chen (University of Science and Technology of China); Bihan Wen (Nanyang Technological University); Robby Tan (National University of Singapore); Radu Timofte (University of Würzburg) et al

[21:20 UTC] 16:20 STRRNet: Semantics-guided Two-stage Raindrop Removal Network
Qiyu Rong (Beijing Union University); Hongyuan Jing (Beijing Union University)*; Mengmeng Zhang (Beijing Union University); Jinlong Li (Beijing Union University); Mengfei Han (Beijing Union University)

[21:25 UTC] 16:25
Challenge Report:"Cross-Domain Few-Shot Object Detection"
Yuqian Fu et al.
[21:30 UTC] 16:25 NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
Yuqian Fu (INSAIT)*; xingyu qiu (fudan); bin ren (unitn); yanwei fu (fudan); Radu Timofte (University of Wurzburg); nicu sebe (University of Trento); Ming-Hsuan Yang (University of California at Merced,); Van Gool Luc (insait) et al

[21:40 UTC] 16:35 Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection
Jiancheng Pan (Tsinghua University)*; Yanxing Liu (University of Chinese Academy of Sciences); Xiao He (Wuhan University); Long Peng (University of Science and Technology of China); Jiahao Li (Tsinghua University); Yuze Sun (Tsinghua University); Xiaomeng Huang (Tsinghua University)

[21:45 UTC] 16:40 Instance Features Caching for Cross-Domain Few-shot Object Detection
Yali Huang (Zhengzhou University); Jie Mei (Zhengzhou University); Yiming Yang (Zhengzhou University); Mi Guo (Zhengzhou University); Mingyuan Jiu (Zhengzhou University)*; Mingliang Xu (Zhengzhou University)

[21:50 UTC] 16:45 - 17:00
Place Holder

[22:00 UTC] 17:00-19:00
Poster Session (17:00-19:00), ExHall D

papers (pdf, suppl. mat) will be available at https://openaccess.thecvf.com/menu
Each paper has an poster panel # allocated in the poster session 17:00-19:00, ExHall D.
The posters should be placed at the beginning of the poster session and removed at the end.


(Poster Board # 264 , NTIRE ID 2 Rethinking Compressive Sensing: A Compression Framework for Video Super-Resolution
Ruthy Katz (Corephothonics)*; Adi Teitel (Corephotonics); Moran Mordechay (Corephotonics); Adi Falik (Corephotonics); Eli Bery (Corephotonics); Maya Mayberg (Corephotonics)
(Poster Board # 265 , NTIRE ID 3 MAD: Makeup All-in-One with Cross-Domain Diffusion Model
Bo-Kai Ruan (National Yang Ming Chiao Tung University)*; Hong-Han Shuai (National Yang Ming Chiao Tung University)
(Poster Board # 266 , NTIRE ID 4 conSAMmé: Achieving Consistent Segmentations with SAM
Josh Myers-Dean (University of Colorado, Boulder)*; Kangning Liu (Adobe Research); Brian Price (Adobe Research); Yifei Fan (Adobe Research); Jason Kuen (Adobe Research); Danna Gurari (University of Colorado, Boulder)
(Poster Board # 267 , NTIRE ID 9 STAPLE: Siamese Transformer Assisted Pseudo Label Ensembling for Unsupervised Domain Adaptation in No-Reference IQA
Arshita Gupta (Samsung Research America)*; Zhe Zhu (Samsung Research America); Tien Bau (Samsung Research America)
(Poster Board # 268 , NTIRE ID 14 XYScanNet: A State Space Model for Single Image Deblurring
Hanzhou Liu (Texas A&M University)*; Chengkai Liu (Texas A&M University); Jiacong Xu (Johns Hopkins University); Peng Jiang (Texas A&M University); Mi Lu (Texas A&M University)
(Poster Board # 269 , NTIRE ID 20 Text-Guided Patch Scoring and Local Distortion Guidance for Image Quality Assessment
Juyong Park (Inha University); Jihun Song (Ulsan National Institute of Science and Technology (UNIST)); Gyewan Kim (Inha University); Yoonsuk Hyun (Inha University)*
(Poster Board # 270 , NTIRE ID 24 Exploring Real&Synthetic Dataset and Linear Attention in Image Restoration
Yuzhen Du (Shanghai Jiao Tong University)*; Teng Hu (ShangHai JiaoTong University); Jiangning Zhang (Tencent); Ran Yi (ShangHai JiaoTong University); Kai Wu (Tencent); Chengming Xu (Tencent); Xiaobin Hu (Tencent); Donghao Luo (Tencent); Yabiao Wang (Tencent); Lizhuang Ma (ShangHai JiaoTong University)
(Poster Board # 271 , NTIRE ID 25 MFSR-GAN: Multi-Frame Super-Resolution with Handheld Motion Modeling
Fadeel Sher Khan (The University of Texas at Austin)*; Joshua Ebenezer (Samsung Research America); Hamid Sheikh (Samsung Research America); Seok-Jun Lee (Samsung Research America)
(Poster Board # 272 , NTIRE ID 29 Training Neural Networks on RAW and HDR Images for Restoration Tasks
Andrew Yanzhe Ke (University of Cambridge); Lei Luo (Meta); Xiaoyu Xiang (Meta); Yuchen Fan (Meta); Rakesh Ranjan (Meta); Alexandre Chapiro (Meta); Rafal Mantiuk (University of Cambridge)*
(Poster Board # 273 , NTIRE ID 31 DataFormer: Differential Additive Transformer for Lightweight Semantic Segmentation
Mian Muhammad Naeem Abid (University of Würzburg)*; Nancy Mehta (University of Würzburg); Zongwei Wu ( University of Würzburg); Radu Timofte (University of Würzburg)
(Poster Board # 274 , NTIRE ID 33 KernFusNet: Implicit Kernel Modulation and Fusion for Blind Super-resolution
Nancy Mehta (Universität Würzburg)*; Akshay Dudhane (MBZUAI); Subrahmanyam Murala (Trinity College Dublin); Radu Timofte (Universität Würzburg)
(Poster Board # 275 , NTIRE ID 36 FUSION: Frequency-guided Underwater Spatial Image recOnstructioN
Jaskaran Walia (Vellore Institute of Technology )*; Shravan Venkatraman (Vellore Institute of Technology); Pavithra L K (Vellore Institute of Technology)
(Poster Board # 276 , NTIRE ID 40 FALCON: Fast Image Haze Removal Leveraging Continuous Density Mask
Donghyun Kim (Yonsei University); Seil Kang (Yonsei University); Seong Jae Hwang (Yonsei University)*
(Poster Board # 277 , NTIRE ID 43 Efficient Burst Super-Resolution with One-step Diffusion
Kento Kawai (TTI-J); Takeru Oba (TTI-J); Kyotaro Tokoro (TTI-J); Kazutoshi Akita (TTI-J); Norimichi Ukita (TTI-J)*
(Poster Board # 278 , NTIRE ID 44 SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimation
Mykola Lavreniuk (Space Research Institute)*; Alla Lavreniuk (National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute»)
(Poster Board # 279 , NTIRE ID 48 FCTFANet: A Fused CNN-Transformer Feature Aggregator Network for Image Restoration
Amit Monga (IIT Roorkee); Hemkant Nehete (IIT Roorkee); Partha Kaushik (IIT Roorkee); THARUN KUMAR REDDY BOLLU (IIT Roorkee)*; Balasubramanian Raman (IIT Roorkee); Gaurav Sharma (University of Rochester)
(Poster Board # 280 , NTIRE ID 50 A Simple Combination of Diffusion Models for Better Quality Trade-Offs in Image Denoising
Jonas Dornbusch (Technical University Munich)*; Emanuel Pfarr (University of Würzburg); Florin-Alexandru Vasluianu (University of Würzburg); Frank Werner (University of Würzburg); Radu Timofte (University of Würzburg)
(Poster Board # 281 , NTIRE ID 51 PromptNorm: Image Geometry Guides Ambient Light Normalization}
David Serrano-Lozano (Computer Vision Center)*; Francisco A. Molina-Bakhos (Computer Vision Center); Danna Xue (Computer Vision Center); Yixiong Yang (Computer Vision Center); Maria Pilligua (Computer Vision Center); Ramon Baldrich (Computer Visino Center); Maria Vanrell (Computer Vision Center); Javier Vazquez-Corral (Computer Vision Center)
(Poster Board # 282 , NTIRE ID 52 The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report
Bin Ren (University of Trento); Hang Guo (Tsinghua University); Lei Sun (INSAIT); Zongwei Wu (University of Wurzburg); Radu Timofte (University of Wurzburg); Yawei Li (ETH Zürich)*
(Poster Board # 283 , NTIRE ID 53 Espanded SPAN for Efficient Super-Resolution
qing wang (bytedance)*; yan wang (bytedance); hongyu an (bytedance); yi liu (bytedance); liou zhang (bytedance); shijie zhao (bytedance)
(Poster Board # 284 , NTIRE ID 58 Leveraging Multimodal Large Language Models for Joint Discrete and Continuous Evaluation in Text-to-Image Alignment
Zhichao Zhang (Shanghai Jiao Tong University)*; Xinyue Li (Shanghai Jiao Tong University); Wei Sun (Shanghai Jiao Tong University); Zicheng Zhang (Shanghai Jiao Tong University); Yunhao Li (Shanghai Jiao Tong University); Xiaohong Liu (Shanghai Jiao Tong University); Guangtao Zhai (Shanghai Jiao Tong University)
(Poster Board # 285 , NTIRE ID 59 NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
Pierluigi Zama Ramirez (University of Bologna)*; Fabio Tosi (University of Bologna); Luigi Di Stefano (University of Bologna); Radu Timofte (University of Wurzburg, Germany); Alex Costanzino (University of Bologna); Matteo Poggi (University of Bologna); Samuele Salti (University of Bologna); Stefano Mattoccia (University of Bologna); Aryan Shukla (École de technologie supérieure (ÉTS), Montréal); Liam Frija-Altarac (École de technologie supérieure (ÉTS), Montréal , Canada); Matthew Toews (École de technologie supérieure (ÉTS), Montréal , Canada); Mykola Lavreniuk (Space Research Institute NASU-SSAU, Kyiv, Ukraine); Hui Geng (National University of Defense Technology, Changsha, China); Tianjiao Wan (National University of Defense Technology, Changsha, China); Zijian Gao (National University of Defense Technology, Changsha, China); Qisheng Xu (National University of Defense Technology, Changsha, China); Kele Xu (National University of Defense Technology, Changsha, China); Zijian Zang (Fudan University); Wu Chen (Beijing University of Posts and Telecommunications); Anlong Ming (Beijing University of Posts and Telecommunications); Mingshuai Zhao (Beijing University of Posts and Telecommunications); Mengying Yu (Beijing University of Posts and Telecommunications); Shida Gao (Beijing University of Posts and Telecommunications); Xiangfeng Wang (Beijing University of Posts and Telecommunications); Feng Xue (University of Trento); Jun Shi (Samsung R&D Institute China-Beijing (SRC-B)); Yong Yang (Samsung R&D Institute China-Beijing (SRC-B)); Yong A (Samsung R&D Institute China-Beijing (SRC-B)); Yixiang Jin (Samsung R&D Institute China-Beijing (SRC-B)); Dingzhe Li (Samsung R&D Institute China-Beijing (SRC-B)); Zhe Zhang (Nanjing University of Science and Technology); Yang Yang (Nanjing University of Science and Technology); Jameer Babu (None); Kuldeep Purohit (None); Jing Cao (Harbin Institute of Technology); Shenyi Li (Harbin Institute of Technology); Kui Jiang (Harbin Institute of Technology); Junjun Jiang (Harbin Institute of Technology);  Yong Huang (Harbin Institute of Technology)
(Poster Board # 286 , NTIRE ID 60 NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results
Sangmin Lee (Samsung Electronics MX Business - Camera Innovation Group)*; Eunpil Park (Samsung Electronics MX Business - Camera Innovation Group); Angel Canelo (Samsung Electronics MX Business - Camera Innovation Group); Hyunhee Park (Samsung Electronics MX Business - Camera Innovation Group); Youngjo Kim (Samsung Electronics MX Business - Camera Innovation Group); Hyungju Chun (Samsung Electronics MX Business - Camera Innovation Group); Xin Jin ( Nankai University); Chongyi Li (Nankai University); Chun-Le Guo (Nankai University); Radu Timofte (University of Wurzburg); Qi Wu (Imvision); Tianheng Qiu (Imvision); Yuchun Dong (Imvision); Shenglin Ding (Imvision); Guanghua Pan (Imvision); Weiyu Zhou (Northwestern Polytechnical University); Tao Hu (Northwestern Polytechnical University); Yixu Feng (Northwestern Polytechnical University); Duwei Dai (Second Affiliated Hospital Of Xi'an Jiaotong University); Yu Cao (Xi'an Institute of Optics and Precision Mechanics of CAS); Peng Wu (Northwestern Polytechnical University); Wei Dong (Xi’an University of Architecture and Technology); Yanning Zhang (Northwestern Polytechnical University); Qingsen Yan (Northwestern Polytechnical University); Simon Larsen (Esoft); Senyan Xu (University of Science and Technology of China); Xingbo Wang (University of Science and Technology of China); Ruixuan Jiang (University of Science and Technology of China); Xin Lu (University of Science and Technology of China); Marcos Conde (Cidaut AI); Javier Abad-Hernández (Cidaut AI); Álvaro García-Lara (Cidaut AI); Daniel Feijoo (Cidaut AI); Álvaro García (Cidaut AI); Zeyu Xiao (National University of Singapore); Zhuoyuan Li (University of Science and Technology of China)
(Poster Board # 287 , NTIRE ID 61 Flow-Guided Deformable Alignment with Channel-wise Self-Attention Reconstruct for Efficient Burst HDR Restoration
Weiyu Zhou (Northwestern Polytechnical University)*; Tao Hu (Northwestern Polytechnical University); Yixu Feng (Northwestern Polytechnical University); Duwei Dai (Second Affiliated Hospital Of Xi'an Jiaotong University); Yu Cao (Xi'an Institute of Optics and Precision Mechanics of CAS); Peng Wu (Northwestern Polytechnical University); Wei Dong  (Xi’an University of Architecture and Technology); Yanning Zhang (Northwestern Polytechnical University); Qingsen Yan (Northwestern Polytechnical University)
(Poster Board # 288 , NTIRE ID 62 FusionNet: Multi-model Linear Fusion Framework for Low-light Image Enhancement
Kangbiao Shi (Northwestern Polytechnical University)*; Yixu Feng (Northwestern Polytechnical University); Tao Hu (Northwestern Polytechnical University); Yu Cao (Xi’an Institute of Optics and Precision Mechanics of CAS); Peng Wu (Northwestern Polytechnical University); Yijin Liang (Shanghai Institute of Satellite Engineering, Shanghai 201109, China); Yanning Zhang (Northwestern Polytechnical University); Qingsen Yan (Northwestern Polytechnical University)
(Poster Board # 289 , NTIRE ID 63 Recursive Multi-Exposure Alignment with Spatiotemporal Decoupling for Efficient Burst HDR and Restoration
Tianheng Qiu (University of Science and Technology of China)*; Qi Wu (Imvision); Yuchun Dong (Imvision); Shenglin Ding (Imvision); Guanghua Pan (Imvision); Xuan Huang (Hefei Institutes of Physical Science, Chinese Academy of Sciences); Hu Wei (Hefei Institutes of Physical Science, Chinese Academy of Sciences)
(Poster Board # 290 , NTIRE ID 64 NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results.
Yuqian Fu (INSAIT)*; xingyu qiu (fudan); bin ren (unitn); yanwei fu (fudan); Radu Timofte (University of Wurzburg); nicu sebe (University of Trento); Ming-Hsuan Yang (University of California at Merced,); Van Gool Luc (insait)
(Poster Board # 291 , NTIRE ID 65 Advancing Ambient Lighting Normalization via Diffusion Shadow Generation
Xin Lu (University of Science and Technology of China); Jiarong Yang (University of Science and Technology of China); Yuanfei Bao (University of Science and Technology of China); Anya Hu (University of Science and Technology of China); Zihao Fan (University of Science and Technology of China); Kunyu Wang (University of Science and Technology of China); Jie Xiao (University of Science and Technology of China); Xi Wang (University of Science and Technology of China); Xueyang Fu (University of Science and Technology of China)*; Zheng-Jun Zha (University of Science and Technology of China)
(Poster Board # 292 , NTIRE ID 66 EvenFormer: Dynamic Even Transformer for Real-World Image Restoration
Xin Lu (University of Science and Technology of China); Yuanfei Bao (University of Science and Technology of China); Jiarong Yang (University of Science and Technology of China); Jie Xiao (University of Science and Technology of China); Kunyu Wang (University of Science and Technology of China); Dong Li (University of Science and Technology of China); Senyan Xu (University of Science and Technology of China); Kean Liu (University of Science and Technology of China); Xueyang Fu (University of Science and Technology of China)*; Zheng-Jun Zha (University of Science and Technology of China)
(Poster Board # 293 , NTIRE ID 67 NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results
Xin Li (University of Science and Technology of China)*; Kun Yuan (Kuaishou Technology); Bingchen Li (University of Science and Technology of China); Fengbin Guan (University of Science and Technology of China); Yizhen Shao (Kuaishou Technology); Zihao Yu (University of Science and Technology of China); Xijun Wang (University of Science and Technology of China); Yiting Lu (University of Science and Technology of China); Wei Luo (University of Science and Technology of China); Suhang Yao (University of Science and Technology of China); Ming Sun (Kuaishou Technology); Chao Zhou (Beijing Kuaishou Technology Co., Ltd); Zhibo Chen (University of Science and Technology of China); Radu Timofte (University of Wurzburg & ETH Zurich)
(Poster Board # 294 , NTIRE ID 68 NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment
Shuhao Han (Nankai University)*; Haotian Fan (Bytedance); Fangyuan Kong (Bytedance); Wenjie Liao (Bytedance); Chunle Guo (Nankai University); Chongyi Li (Nankai University); Radu Timofte (University of Würzburg); Jianhui Sun (WeChat); Zijian Zhang (Meituan); Trong-Hieu Nguyen-Mau (University of Science, VNU-HCM); Jun Lan (Ant Group); Zhichao Zhang (Shanghai Jiao Tong University); Zitong Xu (Shanghai JiaoTong University); Zichuan Wang (Institute of Automation, Chinese Academy of Sciences); Fengbin Guan (University of Science and Technology of China); Minhao Lin (Hangzhou Dianzi University); Xuanxuan He (NationalUniversity of Defense Technology); Bo-Cheng Qiu (National Cheng Kung University); Bo Yu (Beijing University of Posts and Telecommuni-cations); Zhiyu Wang (Hunan University); Shuai He (OPDAI,Netease Game,Guangzhou China); Zhishan Qiao (-); Zewen Chen (State Key Laboratory of Multimodal Artificial IntelligenceSystem, Institute of Automation, Chinese Academy of Sciences); Zeming Liu (OPPO AI Center); Jun Luo (Antgroup); Junfeng Yang (Xiangjiang Laboratory, Hunan University of Technology and Business)
(Poster Board # 295 , NTIRE ID 69 NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study
Xin Li (University of Science and Technology of China)*; Xijun Wang (University of Science and Technology of China); Bingchen Li (University of Science and Technology of China); Kun Yuan (Kuaishou Technology); Yizhen Shao (Kuaishou Technology); Suhang Yao (University of Science and Technology of China); Ming Sun (Kuaishou Technology); Chao Zhou (Beijing Kuaishou Technology Co., Ltd); Radu Timofte (University of Wurzburg & ETH Zurich); Zhibo Chen (University of Science and Technology of China)
(Poster Board # 296 , NTIRE ID 70 NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
Xin Li (University of Science and Technology of China)*; Yeying Jin (National University of Singapore); Xin Jin (Eastern Institute of Technology, Ningbo); Zongwei Wu (University of Würzburg); Bingchen Li (University of Science and Technology of China); Yufei Wang (Snap Research); Wenhan Yang (Pengcheng Laboratory); Yu Li (IDEA); Zhibo Chen (University of Science and Technology of China); Bihan Wen (Nanyang Technological University); Robby Tan (National University of Singapore); Radu Timofte (University of Würzburg)
(Poster Board # 297 , NTIRE ID 71 LFTramba: Comprehensive Information Learning for Light Field Image Super-Resolution via A Hybrid Transformer-Mamba Framework
liu haosong (Huaqiao University)*; zhu xiancheng (Huaqiao University); zeng huanqiang (Huaqiao University); zhu jianqing (Huaqiao University); shi yifan (Huaqiao University); chen jing (Huaqiao University); hou junhui (City University of Hong Kong)
(Poster Board # 298 , NTIRE ID 72 NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution
Marcos Conde (University of Würzburg & Sony PlayStation)*; Radu Timofte (University of Würzburg)
(Poster Board # 299 , NTIRE ID 74 NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and Results
Varun Jain (Microsoft)*; Zongwei Wu (University of Wurzburg); Quan Zou (Microsoft); Louis Florentin (Microsoft); Henrik Turbell (Microsoft); Sandeep Siddhartha (Microsoft); Radu Timofte (University of Wurzburg)
(Poster Board # 300 , NTIRE ID 75 LFTransMamba: A Hybrid Mamba-Transformer Model for Light Field Image Super-Resolution
Kai Jin (Bigo Technology Pte. Ltd.); Zeqiang Wei (Beijing University of Posts and Telecommunications); Angulia Yang (Bigo Technology Pte. Ltd.); Di Wu (Beijing University of Posts and Telecommunications); Mingzhi Gao (Bigo Technology Pte. Ltd.); Xiuzhuang Zhou (Beijing University of Posts and Telecommunications)*
(Poster Board # 301 , NTIRE ID 76 NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results
Xiaoning Liu (University of Electronic Science and Technology of China); Zongwei Wu (University of Wurzburg)*; Florin-Alexandru Vasluianu (University of Wurzburg); Hailong Yan (University of Electronic Science and Technology of China); Bin Ren (University of Trento); Yulun Zhang (Shanghai Jiao Tong University); Shuhang Gu (University of Electronic Science and Technology of China); Le Zhang (University of Electronic Science and Technology of China); Ce Zhu (University of Electronic Science and Technology of China); Radu Timofte (University of Wurzburg)
(Poster Board # 302 , NTIRE ID 78 Frequency-Prior Enhanced Ambient Lighting Normalization via Visual Perceptual Refinement
Yuanfei Bao (University of Science and Technology of China); Xin Lu (University of Science and Technology of China); Xingbo Wang (University of Science and Technology of China); Jiarong Yang (University of Science and Technology of China); Anya Hu (University of Science and Technology of China); Kunyu Wang (University of Science and Technology of China); Jie Xiao (University of Science and Technology of China); Dong Li (University of Science and Technology of China); Xueyang Fu (University of Science and Technology of China)*; Zheng-Jun Zha (University of Science and Technology of China)
(Poster Board # 303 , NTIRE ID 85 NTIRE 2025 Challenge on Light Field Image Super-Resolution: Methods and Results
Yingqian Wang (National University of Defense Technology)*; Zhengyu Liang (National University of Defense Technology ); Fengyuan Zhang (National University of Defense Technology); Lvli Tian (National University of Defense Technology); Longguang Wang (Aviation University of Air Force); Juncheng Li (Shanghai University); Jungang Yang (National University of Defense Technology); Radu Timofte (University of Würzburg); Yulan Guo (Sun Yat-sen University)
(Poster Board # 304 , NTIRE ID 87 Q-CIDNet: Perceptual Quality aware Color and Intensity Decoupling Network for Video Quality Enhancement
Ajeet Verma (Indian Institute of Technology Jammu)*; Shweta Tripathi (Indian Institute of Technology Jammu); Vinit Jakhetiya (Indian Institute of Technology Jammu); Badri N Subudhi (Indian Institute of Technology Jammu); Sunil Jaiswal (K|Lens GmbH)
(Poster Board # 305 , NTIRE ID 89 RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report
Marcos Conde (University of Würzburg & Sony PlayStation)*; Radu Timofte (University of Würzburg)
(Poster Board # 306 , NTIRE ID 91 NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challenge
Jie Liang (OPPO Research Institute)*; Radu Timofte (University of Wurzburg & ETH Zurich); Qiaosi Yi (The Hong Kong Polytechnic University); Zhengqiang Zhang (The Hong Kong Polytechnic University); Shuaizheng Liu (The Hong Kong Polytechnic University); Lingchen Sun (The Hong Kong Polytechnic University); Rongyuan Wu (The Hong Kong Polytechnic University); Xindong Zhang (OPPO Research Institute); Hui Zeng (OPPO Research Institute); Lei Zhang (Hong Kong Polytechnic University, Hong Kong, China)
(Poster Board # 307 , NTIRE ID 92 TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs
Zijian Zhang (Meituan Inc)*; Xuhui Zheng (Nanjing University); Xuecheng Wu (Xi'an Jiaotong University); Chong Peng (Meituan Inc); Xuezhi Cao (Meituan Inc)
(Poster Board # 308 , NTIRE ID 93 NTIRE 2025 Ambient Lighting Normalization Challenge
Florin-Alexandru Vasluianu (Computer Vision Lab, University of Wurzburg)*; Tim Seizinger (Computer Vision Lab, University of Wurzburg); Zhuyun Zhou (CNRS - Université de Bourgogne); Zongwei Wu (Computer Vision Lab, University of Wurzburg); Radu Timofte (Computer Vision Lab, University of Wurzburg); Yuanfei Bao (University of Science and Technology of China (USTC) ); Xingbo Wang ( University of Science and Technology of China (USTC) ); Xin Lu (University of Science and Technology of China (USTC) ); Jiarong Yang (University of Science and Technology of China (USTC) ); Anya Hu (University of Science and Technology of China (USTC)); Kunyu Wang ( University of Science and Technology of China (USTC)); Jie Xiao ( University of Science and Technology of China (USTC)); Dong Li ( University of Science and Technology of China (USTC)); Xueyang Fu ( University of Science and Technology of China (USTC)); Zheng-Jun Zha ( University of Science and Technology of China (USTC)); Zihao Fan ( University of Science and Technology of China (USTC)); Xi Wang ( University of Science and Technology of China (USTC)); Yurui Zhu ( University of Science and Technology of China (USTC)); Kean Liu (University of Science and Technology of China (USTC)); Senyan Xu ( University of Science and Technology of China (USTC)); Hongjian Liu (University of Science and Technology of China (USTC)); Yupeng Xiao ( University of Science and Technology of China (USTC)); David Serrano-Lozano (Computer Vision Center and Universitat Autònoma de Barcelona); Francisco A. Molina-Bakhos (Computer Vision Center and Universitat Autònoma de Barcelona); Danna Xue ( Computer Vision Center and Universitat Autònoma de Barcelona); Yixiong Yang ( Computer Vision Center and Universitat Autònoma de Barcelona); Maria Pilligua ( Computer Vision Center and Universitat Autònoma de Barcelona); Ramon Baldrich (Computer Vision Center and Universitat Autònoma de Barcelona); Maria Vanrell ( Computer Vision Center and Universitat Autònoma de Barcelona); Javier Vazquez-Corral ( Computer Vision Center and Universitat Autònoma de Barcelona); Xuan Sun (MT Lab, Meitu Inc.); Zijie Lou (MT Lab, Meitu Inc.); Ting Liu (MT Lab, Meitu Inc.); Kuldeep Purohit (Independent Researchers); Jameer Babu Pinjari (Independent Researchers); Yilin Zhang (Hefei University of Technology); Huan Zheng (University of Macau); Yanyan Wei ( Hefei University of Technology); Suiyi Zhao ( Hefei University of Technology); Shengeng Tang ( Hefei University of Technology); Zhao Zhang ( Hefei University of Technology); Yushen Zuo (The Hong Kong Polytechnic University); Zongqi He ( The Hong Kong Polytechnic University); Zhe Xiao ( The Hong Kong Polytechnic University); Cuixin Yang ( The Hong Kong Polytechnic University); Rongkang Dong ( The Hong Kong Polytechnic University); Jun Xiao ( The Hong Kong Polytechnic University); Kin-Man Lam ( The Hong Kong Polytechnic University); Nikhil Akalwadi (School of Computer Science and Engineering, KLE Technological University); Vijayalaxmi Ashok Aralikatti (School of Computer Science and Engineering, KLE Technological University); Dheeraj Damodhar Hegde (School of Electronics and Communication Engineering, KLE Technological University); Ramesh Ashok Tabib ( School of Electronics and Communication Engineering, KLE Technological University); Uma Mudenagudi (School of Electronics and Communication Engineering, KLE Technological University); Anas M. Ali (Robotics and Internet-of-Things Laboratory, Prince Sultan University); Bilel Benjdira (Robotics and Internet-of-Things Laboratory, Prince Sultan University); Wadii Boulila ( Robotics and Internet-of-Things Laboratory, Prince Sultan University)
(Poster Board # 309 , NTIRE ID 97 NTIRE 2025 Challenge on Single Image Reflection Removal in the Wild: Datasets, Methods and Results
Kangning Yang (OPPO AI Center)*; Jie Cai (OPPO AI Center); Ling Ouyang (OPPO AI Center); Florin-Alexandru Vasluianu (University of Würzburg); Radu Timofte (University of Würzburg); Jiaming Ding (OPPO AI Center); Huiming Sun (OPPO AI Center); Lan Fu (OPPO AI Center); Jinlong Li (OPPO AI Center); Chiu Man Ho (OPPO AI Center); Zibo Meng (OPPO AI Center)
(Poster Board # 310 , NTIRE ID 98 NTIRE 2025 Image Shadow Removal Challenge Report
Florin-Alexandru Vasluianu (University of Würzburg); Tim Seizinger (University of Würzburg); Zhuyun Zhou (CNRS - Université de Bourgogne); Cailian Chen (Shanghai Jiao Tong University); Zongwei Wu (University of Wurzburg); Radu Timofte (University of Würzburg); Mingjia Li (Tianjin University); Jin Hu (Tianjin University); Hainuo Wang (Tianjin University); Hengxing Liu (Tianjin University); Jiarui Wang (Tianjin University); Qiming Hu (Tianjin University); Xiaojie Guo (Tianjin University); Xin Lu (University of Science and Technology of China, Hefei); Jiarong Yang (University of Science and Technology of China, Hefei); Yuanfei Bao (University of Science and Technology of China, Hefei); Anya Hu (University of Science and Technology of China, Hefei); Zihao Fan (University of Science and Technology of China, Hefei); Kunyu Wang (University of Science and Technology of China, Hefei); Jie Xiao (University of Science and Technology of China, Hefei); Xi Wang (University of Science and Technology of China, Hefei); Xueyang Fu (University of Science and Technology of China, Hefei); Zheng-Jun Zha (University of Science and Technology of China, Hefei); Yu-Fan Lin (National Cheng Kung University); Chia-Ming Lee (National Cheng Kung University); Chih-Chung Hsu (National Yang Ming Chiao Tung University); Xingbo Wang (University of Science and Technology of China, Hefei); Dong Li (University of Science and Technology of China, Hefei); Yuxu Chen (Fuzhou University); Bin Chen (Fuzhou University); Yuanbo Zhou (Fuzhou University); Yuanbin Chen (Fuzhou University); Hongwei Wang (Fuzhou University); Jiannan Lin (Fuzhou University); Qinquan Gao (Fuzhou University); Tong Tong (Fuzhou University); Yanyan Wei (Hefei University of Technology); Wei Dong (McMaster University); Han Zhou (McMaster University); Seyed Amirreza Mousavi (McMaster University); Jun Chen (McMaster University); Haobo Liang (Lanzhou Jiaotong University); Jiajie Jing (Lanzhou Jiaotong University); Junyu Li (Lanzhou Jiaotong University); Yan Yang (Lanzhou Jiaotong University); Seoyeon Lee (Kookmin University); Chaewon Kim (Kookmin University); Ziyu Feng (Beijing Jiaotong University); Shidi Chen (Beijing Jiaotong University); Bowen Luan (Beijing Jiaotong University); Zewen Chen (Beijing Jiaotong University); Vijayalaxmi Ashok Aralikatti (KLE Technological University); G Gyaneshwar Rao (KLE Technological University); Nikhil Akalwadi (KLE Technological University); Chaitra Desai (KLE Technological University); Ramesh Ashok Tabib (KLE Technological University); Uma Mudenagudi (KLE Technological University); Anas M. Ali (Prince Sultan University); Bilel Benjdira (Prince Sultan University); Wadii Boulila (Prince Sultan University); Alexandru Brateanu (University of Manchester); Cosmin Ancuti (Politehnica University Timisoara); Tanmay Chaturvedi (Sardar Vallabhbhai National Institute of Technology, Surat); Manish Kumar (Sardar Vallabhbhai National Institute of Technology, Surat); Anmol Srivastav (Sardar Vallabhbhai National Institute of Technology, Surat); Daksh Trivedi (Sardar Vallabhbhai National Institute of Technology, Surat); Shashwat Thakur (Sardar Vallabhbhai National Institute of Technology, Surat); Kishor Upla (Sardar Vallabhbhai National Institute of Technology, Surat); Zeyu Xiao (National University of Singapore); Zhuoyuan Li (University of Science and Technology of China, Hefei); Boda Zhou (None)*; Shashank Shekhar (Jawaharlal Nehru University); Kele Xu (National University of Defense Technology); Qisheng Xu (National University of Defense Technology); Zijian Gao (National University of Defense Technology); Tianjiao Wan (National University of Defense Technology)
(Poster Board # 311 , NTIRE ID 99 NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
Lei Sun (Zhejiang University); Andrea Alfarano (INSAIT, Sofia University); Peiqi Duan (Peking University); Shaolin Su (Computer Vision Center)*; Kaiwei Wang (Zhejiang University); Boxin Shi (Peiking University); Radu Timofte (University of Wurzburg); Danda Pani Paudel (INSAIT, Sofia University); Luc Van Gool (INSAIT, Sofia University)
(Poster Board # 312 , NTIRE ID 100 The Tenth NTIRE 2025 Image Denoising Challenge Report
Lei Sun (INSAIT, Sofia University “St. Kliment Ohridski”); Hang Guo (Tsinghua University); Bin Ren (University of Trento); Luc Van Gool (INSAIT, Sofia University “St. Kliment Ohridski”); Radu Timofte (University of Wurzburg); Yawei Li (ETH Zurich)*
(Poster Board # 313 , NTIRE ID 102 STRRNet: Semantics-guided Two-stage Raindrop Removal Network
Qiyu Rong (Beijing Union University); Hongyuan Jing (Beijing Union University)*; Mengmeng Zhang (Beijing Union University); Jinlong Li (Beijing Union University); Mengfei Han (Beijing Union University)
(Poster Board # 314 , NTIRE ID 104 Instruction-augmented Multimodal Alignment for Image-Text and Element Matching
Xinli Yue (Wuhan University); JianHui Sun (WeChat); Junda Lu (WeChat); Liangchao Yao (WeChat); FAN XIA (WeChat); Tianyi Wang (WeChat); Fengyun Rao (WeChat); JING LYU (WeChat); Yuetang Deng (WeChat)*
(Poster Board # 315 , NTIRE ID 105 NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results
Xiaohong Liu (Shanghai Jiao Tong University)*; Xiongkuo Min (Shanghai Jiao Tong University); Qiang Hu (Shanghai Jiao Tong University); Xiaoyun Zhang (Shanghai Jiao Tong University); Jie Guo (Peng Cheng Laboratory); Guangtao Zhai (Shanghai Jiao Tong University); Shushi Wang (Shanghai Jiao Tong University); Yingjie Zhou (Shanghai Jiao Tong University); Lu Liu (Shanghai Jiao Tong University); Jingxin Li (China National Information Technology Standardization Committee Multimedia Subcommittee); Liu Yang (Shanghai Jiao Tong University); Farong Wen (Shanghai Jiao Tong University); Li Xu (Peng Cheng Laboratory); Yanwei Jiang (Shanghai Jiao Tong University); Xilei Zhu (Shanghai Jiao Tong University); Chunyi Li (Shanghai Jiao Tong University); Zicheng Zhang (Shanghai Jiao Tong University); Huiyu Duan (Shanghai Jiao Tong University); Xiele Wu (Shanghai Jiao Tong University); Yixuan Gao (Shanghai Jiao Tong University); Yuqin Cao (Shanghai Jiao Tong University); Jun Jia (Shanghai Jiao Tong University); Wei Sun (Shanghai Jiao Tong University); Jiezhang Cao (Harvard University); Radu Timofte (University of W ̈urzburg)
(Poster Board # 316 , NTIRE ID 106 An Empirical Study for Efficient Video Quality Assessment
Wei Sun (Shanghai Jiao Tong Unviersity)*; Kang Fu (Shanghai Jiao Tong University); Linhan Cao (Shanghai Jiao Tong University); Dandan Zhu (East China Normal University); Kaiwei Zhang (Shanghai Jiao Tong University); Yucheng Zhu (Shanghai Jiao Tong University); Zicheng Zhang (Shanghai Jiao Tong University); Menghan Hu (East China Normal University); Xiongkuo Min (Shanghai Jiao Tong University); Guangtao Zhai (Shanghai Jiao Tong University)
(Poster Board # 317 , NTIRE ID 107 Quality Assessment for Talking Head Videos via Multi-modal Feature Representation
Mengjing Su (China University of Mining and Technology, Jiangsu)*; Yi Wang (China University of Mining and Technology, Jiangsu); Tuo Chen (China University of Mining and Technology, Jiangsu); Chunxiao Li (China University of Mining and Technology, Jiangsu); Shuaiyu Zhao (China University of Mining and Technology, Jiangsu); Jiaxin Wen (China University of Mining and Technology, Jiangsu); Chuyi Lin (China University of Mining and Technology, Jiangsu); Sitong Liu (China University of Mining and Technology, Jiangsu); Ningxin Chu (China University of Mining and Technology, Jiangsu); Yu Zhou (China University of Mining and Technology, Jiangsu)
(Poster Board # 318 , NTIRE ID 108 Enhanced Semantic Extraction and Guidance for UGC Image Super Resolution
Yiwen Wang (Shanghai Jiao Tong University); Ying Liang (Shanghai Jiao Tong University)*; Yuxuan Zhang (Shanghai Jiao Tong University); Xinning Chai (Shanghai Jiao Tong University); Zhengxue Cheng (Shanghai Jiao Tong University); Yingsheng Qin (Transsion); Yucai Yang (Transsion); Rong Xie (Shanghai Jiao Tong University); Li Song (Shanghai Jiao Tong University)
(Poster Board # 319 , NTIRE ID 110 Distillation-Supervised Convolutional Low-Rank Adaptation for Efficient Image Super-Resolution
Xinning Chai (Shanghai Jiao Tong University); Yao Zhang (Shanghai Jiao Tong University)*; Yuxuan Zhang (Shanghai Jiao Tong University); Zhengxue Cheng (Shanghai Jiao Tong University); Yingsheng Qin (Transsion, China); Yucai Yang (Transsion, China); Li Song (Shanghai Jiao Tong University)
(Poster Board # 320 , NTIRE ID 112 Pureformer: Transformer-Based Image Denoising
Arnim Gautam (Government Engineering College Ajmer); Aditi Pawar (Government Engineering College Ajmer); Aishwarya Joshi (Government Engineering College Ajmer); Satya Tazi (Government Engineering College Ajmer); Sachin Chaudhary (UPES Dehradun); Praful Hambarde (IIT Mandi); Akshay Dudhane ( Mohamed bin Zayed University of Artificial Intelligence)*; Santosh Vipparthi (IIT Ropar); Subrahamanyam Murala (IIT Ropar)
(Poster Board # 321 , NTIRE ID 113 LFMix: A Lightweight Hybrid Architecture Model for Light Field Super-Resolution
mingyang yu (East China Normal University)*; zhijian wu (East China Normal University); dingjiang huang (East China Normal University)
(Poster Board # 322 , NTIRE ID 118 Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design
Wei Dong (McMaster University); Yan Min (McMaster University); Han Zhou (McMaster University)*; Jun Chen (McMaster University)
(Poster Board # 323 , NTIRE ID 119 Retinex-Guided Histogram Transformer for Mask-Free Shadow Removal
Wei Dong (McMaster University); Han Zhou (McMaster University)*; Seyed Amirreza Mousavi (McMaster University); Jun Chen (McMaster University)
(Poster Board # 324 , NTIRE ID 120 EV-Deblurformer: A Dual-Branch Network for Event-Guided Motion Deblurring
Kean Liu (University of Science and Technology of China)*; Mingchen Zhong (University of Science and Technology of China); Senyan Xu (University of Science and Technology of China); Zhijing Sun (University of Science and Technology of China); Jiaying Zhu (University of Science and Technology of China); Chengjie Ge (University of Science and Technology of China); Xingbo Wang (University of Science and Technology of China); Xin Lu (University of Science and Technology of China); Xueyang Fu (University of Science and Technology of China); Zheng-Jun Zha (University of Science and Technology of China)
(Poster Board # 325 , NTIRE ID 122 Towards Holistic Visual Quality Assessment of AI-Generated Videos: A LLM-Based Multi-Dimensional Evaluation Model
Zelu Qi (Communication University of China)*; Shi Ping (Communication University of China); Chaoyang Zhang (Communication University of China); Shuqi Wang (Communication University of China); Fei Zhao (Communication University of China); Da Pan (Communication University of China); Zefeng Ying (Communication University of China)
(Poster Board # 326 , NTIRE ID 125 NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results
Nickolay Safonov (MSU)*; Alexey Bryntsev (Lomonosov Moscow State University); Andrey Moskalenko (Lomonosov Moscow State University); Dmitry Kulikov (Lomonosov Moscow State University); Dmitriy Vatolin (Lomonosov Moscow State University); Radu Timofte (University of Würzburg); Haibo Lei (Tencent); Jie Song (DeepView); Peipei Liang (Longyuan (Beijing) New Energy Engineering Technology Co., Ltd.); Yingxue Pang (University of Science and Technology of China); Fangzhou Luo (Bytedance); Mingyang Wu (Texas A&M University); Meisong Zheng (Alibaba)
(Poster Board # 327 , NTIRE ID 126 NTIRE 2025 Challenge on Night Photography Rendering
Egor Ershov (AIRI); Sergey Korchagin (IITP RAS)*; Alexei Khalin (IITP RAS); Artyom Panshin (IITP RAS); Arseniy Terekhin (IITP RAS); Ekaterina Zaychenkova (IITP RAS); Georgiy Lobarev (IITP RAS); Vsevolod Plokhotnyuk (IITP RAS); Denis Abramov (IITP RAS); Elisey Zhdanov (IITP RAS); Sofia Dorogova (IITP RAS); Yasin Mamedov (IITP RAS); Nikola Baniс (Gideon Brothers); Georgii Perevozchikov (University of Wurzburg); Radu Timofte (University of Wurzburg); Lize Zhang (Xiaomi Inc); Yuqian Zhang (Xiaomi Inc); Shuai Liu (Xiaomi Inc); Chaoyu Feng (Xiaomi Inc); Luyang Wang (Xiaomi Inc); Yibin Huang (Xiaomi Inc); Guangqi Shao (Xiaomi Inc); Xiaotao Wang (Xiaomi Inc); Lei Lei (Xiaomi Inc); Sishun Pan (Nanjing University of Science and Technology); Zhiqiang Zhong (Nanjing University of Science and Technology); Yang Yang (Nanjing University of Science and Technology); Anas M. Ali (Prince Sultan University); Hamad Aloqayli (Prince Sultan University); Bilel Benjdira (Prince Sultan University); Wadii Boulila (Prince Sultan University); Ma Xiaoyang (China Agriculture University); Gao Zijun (China Agriculture University); Xing Leyi (Beihang University); Zongqi He (The Hong Kong Polytechnic University); Yushen Zuo (The Hong Kong Polytechnic University); Zhe Xiao (The Hong Kong Polytechnic University); Kin-Chung Chan (The Hong Kong Polytechnic University); Hanmin Li (Sun Yat-sen University); Jun Xiao (The Hong Kong Polytechnic University); Kin-Man Lam (The Hong Kong Polytechnic University); Yunpeng Wu (Nanchang University); Dmitrij Manzura (ITMO University); Daniil Storonkin (ITMO University); Weixin Guo (National University of Defense Technology); Kele Xu (National University of Defense Technology); Qisheng Xu (National University of Defense Technology); Zijian Gao (National University of Defense Technology); Tianjiao Wan (National University of Defense Technology); Buda Vampilov (ITMO University); Furkan Kınlı (Ozyegin University); Furkan Kıraç (T-Fashion Inc)
(Poster Board # 328 , NTIRE ID 129 NTIRE 2025 Challenge on Image Super-Resolution (×4): Methods and Results
Zheng Chen (Shanghai Jiao Tong University); Kai Liu (Shanghai Jiao Tong University); Jue Gong (Shanghai Jiao Tong University); Jingkai Wang (Shanghai Jiao Tong University); Lei Sun (ETH Zurich); Zongwei Wu (University of Wurzburg); Radu Timofte (University of Wurzburg & ETH Zurich); Yulun Zhang (Shanghai Jiao Tong University)*
(Poster Board # 329 , NTIRE ID 130 NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results
Zheng Chen (Shanghai Jiao Tong University); Jingkai Wang (Shanghai Jiao Tong University); Kai Liu (Shanghai Jiao Tong University); Jue Gong (Shanghai Jiao Tong University); Lei Sun (ETH Zurich); Zongwei Wu (University of Wurzburg); Radu Timofte (University of Wurzburg & ETH Zurich); Yulun Zhang (hanghai Jiao Tong University)*
(Poster Board # 330 , NTIRE ID 132 Enhance Then Search: An Augmentation-Search Strategy for Cross-Domain Few-Shot Object Detection
Jiancheng Pan (Tsinghua University)*; Yanxing Liu (University of Chinese Academy of Sciences); Xiao He (Wuhan University); Long Peng (University of Science and Technology of China); Jiahao Li (Tsinghua University); Yuze Sun (Tsinghua University); Xiaomeng Huang (Tsinghua University)
(Poster Board # 331 , NTIRE ID 133 Multi-Dimensional Quality Assessment for UGC Videos via Modular Multi-Modal Vision-Language Models
Weixia Zhang (Shanghai Jiao Tong University)*; Bingkun Zheng (Shanghai Jiao Tong University); Junlin Chen (Shanghai Jiao Tong University); Zhihua Wang (City University of Hong Kong)
(Poster Board # 332 , NTIRE ID 135 Instance Features Caching for Cross-Domain Few-shot Object Detection
Yali Huang (Zhengzhou University); Jie Mei (Zhengzhou University); Yiming Yang (Zhengzhou University); Mi Guo (Zhengzhou University); Mingyuan Jiu (Zhengzhou University)*; Mingliang Xu (Zhengzhou University)

NTIRE 2025 Award Certificates (TBU)

Contact:

Radu Timofte, radu.timofte@uni-wuerzburg.de

Computer Vision Laboratory, University of Wurzburg, Germany