• Radu Timofte, University of Wurzburg,
• Andrey Ignatov, AI Benchmark and ETH Zurich,
• Marcos V. Conde, University of Wurzburg and Sony,
• Zongwei Wu, University of Wurzburg
• Dmitriy Vatolin, Moscow State University,
• George Ciubotariu, University of Wurzburg
• Georgii Perevozchikov, University of Wurzburg
• Andrei Dumitriu, University of Wurzburg
• Florin Vasluianu, University of Wurzburg
• Chao Wang, Max Planck Institute for Informatics
• Nikolai Karetin, Lomonosov Moscow State University
• Nikolay Safonov, Lomonosov Moscow State University
• Alexander Yakovenko, Lomonosov Moscow State University

• Mahmoud Afifi, Google
• Cosmin Ancuti, UPT
• Michael S. Brown, York University
• Jiezhang Cao, ETH Zurich
• Sunghyun Cho, Samsung
• Marcos V. Conde, University of Wurzburg
• Touradj Ebrahimi, EPFL
• Corneliu Florea, University Politechnica of Bucharest
• Peter Gehler, Zalando / Amazon
• Jinjin Gu, INSAIT
• Shuhang Gu, University of Electronic Science and Technology of China
• Chiu Man Ho, OPPO,
• Hiroto Honda, GO Inc.
• Andrey Ignatov, ETH Zurich
• Eddy Ilg, University of Technology Nuremberg
• Jan Kautz, NVIDIA
• Christian Ledig, University of Bamberg
• Yawei Li, ETH Zurich
• Stephen Lin, Microsoft Research
• Kai-Kuang Ma, Nanyang Technological University, Singapore
• Vasile Manta, Technical University of Iasi
• Rafal Mantiuk, University of Cambridge
• Zibo Meng, OPPO
• Yusuke Monno, Tokyo Institute of Technology
• Karol Myszkowski, MPI-Informatik
• Vinay P. Namboodiri, University of Bath
• Michael Niemeyer, Google
• Sylvain Paris, Adobe Research
• Aline Roumy, INRIA
• Nicu Sebe, University of Trento
• Gregory Slabaugh, Queen Mary University of London
• Hugues Talbot, Centralesupelec
• Masayuki Tanaka, Tokyo Institute of Technology
• Hao Tang, Peking University
• Jean-Philippe Tarel, G. Eiffel University
• Qi Tian, Huawei Cloud & AI
• Radu Timofte, University of Wurzburg
• George Toderici, Google
• Luc Van Gool, ETH Zurich & KU Leuven
• Yingqian Wang, National University of Defense Technology
• Zhou Wang, University of Waterloo
• Gordon Wetzstein, Stanford University
• Ming-Hsuan Yang, University of California at Merced & Google
• Ren Yang, Microsoft
• Wenjun Zeng, Microsoft Research
• Kai Zhang, Nanjing University
• Yulun Zhang, Shanghai Jiao Tong University
• Jun-Yan Zhu, Carnegie Mellon University
• Wangmeng Zuo, Harbin Institute of Technology

Vishal M. Patel

Johns Hopkins University

Title: Two Perspectives on Image Manipulation: Restoration and Implicit Representations

Abstract: This talk presents two complementary perspectives on image manipulation: image restoration and implicit neural representations. I will first discuss our recent advances in image restoration, spanning GAN-based approaches for de-raining, de-hazing, and all-weather removal. I will highlight key challenges in this domain, particularly issues related to identity preservation, sample replication, and bias observed in both diffusion and generative models. In the second part, I will introduce our ongoing work on implicit neural representations (INRs) and explore how these continuous models can provide new insights for image quality assessment and representation learning. Together, these directions aim to push the boundaries of faithful and interpretable image manipulation.

Bio: Vishal M. Patel is an Associate Professor in the Department of Electrical and Computer Engineering (ECE) at Johns Hopkins University. His research focuses on computer vision, machine learning, image processing, medical image analysis, and biometrics. He has received a number of awards including the 2021 IEEE Signal Processing Society (SPS) Pierre-Simon Laplace Early Career Technical Achievement Award, the 2021 NSF CAREER Award, the 2021 IAPR Young Biometrics Investigator Award (YBIA), the 2016 ONR Young Investigator Award, and the 2016 Jimmy Lin Award for Invention. Patel serves as an associate editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence journal and IEEE Transactions on Biometrics, Behavior, and Identity Science. He also chairs the conference subcommittee of IAPR Technical Committee on Biometrics (TC4). He is a fellow of the IAPR.

Nupur Kumari

Carnegie Mellon University

Title: Customizing Text-to-Image Diffusion Models

Abstract: With the rapid advancement of generative models, their potential to transform creative content creation is increasingly evident. However, most large-scale generative models are primarily text-conditioned, given the availability of large-scale paired text–image datasets. In contrast, for most practical applications, creators often begin from an existing asset and wish to generate variations or modify it in specific ways. For images, this may involve placing an object in a new context, adjusting local attributes, or altering visual style. To tackle the challenge of lack of paired data, in this talk, I will first present our work on constructing a synthetic paired dataset for the personalization task using the capabilities of pre-trained generative models themselves. In the end I will also share some of our recent work on training without paired supervision. We instead leverage vision–language models to evaluate task success and provide direct gradient-based feedback to the generative model. This holds the promise of being a scalable and robust framework for customizing generating models on downstream tasks where there's limited to no supervised paired data.

Bio: Nupur is a PhD student at the Robotics Institute, Carnegie Mellon University, advised by Prof. Jun-Yan Zhu. Her research focuses on generative models, with an emphasis on fine-tuning techniques for customization, controllability, and responsible content generation. She holds a bachelor’s degree in Mathematics and Computing from the Indian Institute of Technology Delhi. Prior to starting her PhD, she worked as a Machine Learning Engineer at Adobe India. She has interned at Meta and Adobe Research and is a 2025 WiGRAPH Rising Star in Computer Graphics.

Sergey Tulyakov

Snap In.

Title: Three and a Half Generations of Video Generation Models

Abstract: Come to the talk and you will know it!

Bio: Sergey Tulyakov is the Director of Research at Snap Inc., where he leads the Creative Vision team. Sergey’s work focuses on building technology to enhance creators’ skills using computer vision, machine learning, and generative AI. His work involves 2D, 3D, video generation, editing, and personalization. To scale generative experiences to hundreds of millions of users, Sergey’s team builds the world’s most efficient mobile foundational models, which enhance multiple products at Snap Inc. Sergey pioneered video generation and unsupervised animation domains with MoCoGAN, MonkeyNet, and the First Order Motion Model, sparking several startups in the field. His work on Interactive Video Stylization received the Best in Show Award at SIGGRAPH Real-Time Live! 2020. He has published over 60 top conference papers, journals, and patents, resulting in multiple innovative products, including Real-time Neural Lenses, real-time try-on, Snap AI Video, Imagine Together, world's fastest foundational image-to-image model and many more. Before joining Snap Inc., Sergey was with Carnegie Mellon University, Microsoft, and NVIDIA. He holds a PhD from the University of Trento, Italy.

Varun Jampani

Arcade.AI

Title: Crafting Video Diffusion: Precise Controls and Rich Outputs

Abstract: In this talk, I will give an overview of our recent works on video generative models that enables precise input controls and rich outputs resulting in a range of 2D, 3D and 4D applications. Specifically, I will talk about the following works with precise input controls: Structured taxonomy controls (Stable Cinemetrics, NeurIPS’25) for professional movie making; Precise 3D camera control (Stable Virtual Camera, ICCV’25); Expression Control (Stable Video-driven Portraits). In the later part of the talk, I will give an overview of the works with rich outputs enabling 3D and 3D generations: Spatio-temporal generation (Stable Video 4D 2.0, ICCV’25); Multi-view kinematic part generation (Stable Part Diffusion 4D, NeurIPS’25); Multi-view PBR Material generation (Stable Video Materials 3D, ICCV’25).

Bio: Varun Jampani is Chief AI Officer at Arcade.AI. Previously, he was VP research at Stability AI and also held researcher positions at Google and Nvidia. He works in the areas of machine learning and computer vision and his main research interests include image, video and 3D generation. He obtained his PhD with highest honors at Max Planck Institute for Intelligent Systems (MPI) and University of Tübingen in Germany. He obtained his BTech and MS from International Institute of Information Technology, Hyderabad (IIIT-H), India, where he was a gold medalist. He actively contributes to the research community and regularly serves as area chair and reviewer for major computer vision and machine learning conferences. His works have received ‘Best Paper Honorable Mention’ award at CVPR’18 and 'Best Student Paper Honorable Mention' award at CVPR’23.

Boxin Shi

Peking University

Title: Video Generation with Audio Synchronization and Panorama Representation

Abstract: Generating videos with synchronized audio and expanded filed-of-view overcomes the limitations of traditional media with planar scene representation, thereby enabling a more immersively dynamic visual experience. This talk will introduce two advancements in video generation with audio synchronization and panorama representation. For audio- synchronized video generation, we design a multi-stream temporal ControlNet and a multi-stage training strategy to achieve precise audio-visual synchronization. For panoramic video generation, we propose a latitude-aware sampling, a rotated semantic denoising, and a padded pixel-wise decoding strategy to effectively extend pre-trained text-to-video models to the panoramic domain. Our results demonstrate significant enhancement to the expressive power of existing video generation models, offering new perspectives for automated content creation and the development of dynamic world models.

Bio: Boxin Shi is currently a Boya Young Fellow Associate Professor (with tenure) and Research Professor at Peking University, where he leads the Camera Intelligence Lab. He received the PhD degree from the University of Tokyo and did postdoc research at MIT Media Lab. His research interests are computational photography and computer vision. He has published more than 200 papers, including 32 papers in TPAMI and 100+ papers in CVPR/ICCV/ECCV. His papers were awarded as Best Paper, Runners-Up at CVPR 2024/ICCP 2015, and selected as candidate for Best Paper at ICCV 2015. He received the Okawa Foundation Research Grant in 2021. He has served as an associate editor of TAPMI/IJCV and an area chair of CVPR/ICCV/ECCV. He is a Distinguished Lecturer of APSIPA, a Distinguished Member of CCF, and a Senior Member of the IEEE/CSIG. Please access his lab website for more information: https://camera.pku.edu.cn/