• Radu Timofte, ETH Zurich,
• Luc Van Gool, KU Leuven & ETH Zurich,
• Ming-Hsuan Yang, University of California at Merced & Google,
• Kyoung Mu Lee, Seoul National University,
• Eli Shechtman, Creative Intelligence Lab at Adobe Research,
• Martin Danelljan, ETH Zurich,
• Shuhang Gu, OPPO & University of Sydney,
• Seungjun Nah, Seoul National University,
• Sanghyun Son, Seoul National University,
• Suyoung Lee, Seoul National University,
• Ruofan Zhou, EPFL,
• Majed El Helou, EPFL,
• Sabine Süsstrunk, EPFL,
• Lei Zhang, Alibaba / Hong Konh Polytechnic University
• Michael Brown, York University
• Goutam Bhat, ETH Zurich
• Chao Dong, SIAT
• Cosmin Ancuti, UCL
• Codruta Ancuti, University Politehnica Timisoara
• Eduardo Perez Pellitero, Huawei Noah's Ark Lab
• Ales Leonardis, Huawei Noah's Ark Lab & University of Birmingham
• Oliver Nina, AF Research Lab
• Abdullah Abuolaim, York University
• Jimmy Ren, SenseTime
• Andreas Lugmayr, ETH Zurich
• Bob Lee, Wright Brothers Institute
• Jinjin Gu, SNU
• Ren Yang, ETH Zurich

• Codruta Ancuti, UPT
• Cosmin Ancuti, Polytechnic University of Timisoara
• Boaz Arad, Ben-Gurion University of the Negev
• Siavash Arjomand Bigdeli, CSEM
• Nick Barnes, Australian National University
• Michael S. Brown, York University
• Cheng-Ming Chiang, MediaTek
• Sunghyun Cho, POSTECH
• Martin Danelljan, ETH Zurich
• Tali Dekel, Weizmann Institute of Science
• Touradj Ebrahimi, EPFL
• Chao Dong, SIAT
• Weisheng Dong, Xidian University
• Touradj Ebrahimi, EPFL
• Majed El Helou, EPFL
• Graham Finlayson, University of East Anglia
• Corneliu Florea, University Politechnica of Bucharest
• Peter Gehler, Amazon
• Bastian Goldluecke, University of Konstanz
• Shuhang Gu, OPPO & University of Sydney
• Christine Guillemot, INRIA
• Felix Heide, Princeton University & Algolux
• Chiu Man Ho, OPPO,
• Hiroto Honda, Mobility Technologies Co Ltd.
• Zhe Hu, Hikvision Research
• Zhiwu Huang, ETH Zurich
• Andrey Ignatov, ETH Zurich
• Seon Joo Kim, Yonsei University
• In So Kweon, KAIST
• Christian Ledig, VideaHealth
• Suyoung Lee, Seoul National University
• Kyoung Mu Lee, Seoul National University
• Seungyong Lee, POSTECH
• Victor Lempitsky, Skoltech & Samsung
• Ales Leonardis, Huawei Noah's Ark Lab & University of Birmingham
• Yawei Li, ETH Zurich
• Stephen Lin, Microsoft Research
• Ming-Yu Liu, NVIDIA Research
• Vladimir Lukin, National Aerospace University
• Kai-Kuang Ma, Nanyang Technological University, Singapore
• Vasile Manta, Technical University of Iasi
• Zibo Meng, OPPO
• Rafael Molina, University of Granada
• Yusuke Monno, Tokyo Institute of Technology
• Seungjun Nah, Seoul National University
• Hajime Nagahara, Osaka University
• Vinay P. Namboodiri, IIT Kanpur
• Federico Perazzi, Facebook
• Fatih Porikli, Qualcomm CR&D
• Hayder Radha, Michigan State University
• Wenqi Ren, Chinese Academy of Sciences
• Antonio Robles-Kelly, Deakin University
• Andres Romero, ETH Zurich
• 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
• Sanghyun Son, Seoul National University
• Sabine Süsstrunk, EPFL
• Yu-Wing Tai, Kuaishou Technology & HKUST
• Hugues Talbot, Université Paris Est
• Masayuki Tanaka, Tokyo Institute of Technology
• Hao Tang, University of Trento
• Jean-Philippe Tarel, IFSTTAR
• Radu Timofte, ETH Zurich
• George Toderici, Google
• Luc Van Gool, ETH Zurich & KU Leuven
• Ashok Veeraraghavan, Rice University
• Jue Wang, Tencent
• Oliver Wang, Adobe Systems Inc
• Ting-Chun Wang, NVIDIA
• Xintao Wang, The Chinese University of Hong Kong
• Ming-Hsuan Yang, University of California at Merced & Google
• Ren Yang, ETH Zurich
• Wenjun Zeng, Microsoft Research
• Kai Zhang, ETH Zurich
• Richard Zhang, UC Berkeley & Adobe Research
• Yulun Zhang, Northeastern University
• Ruofan Zhou, EPFL
• Jun-Yan Zhu, Adobe Research & CMU
• Wangmeng Zuo, Harbin Institute of Technology

Alan Bovik

University of Texas at Austin

Title: Getting “High” on Frame Rates

Abstract: Modern streaming video providers continuously seek to improve consumer experiences by delivering higher-quality, denser content. An important direction that bears study is high-frame rate (HFR) videos, which present unique problems involving balances between frame rate, video quality, and compression. I will describe new large-scale perceptual studies that we have conducted that are focused on these issues. I will also describe new computational video quality models that address highly practical questions, such as frame rate selection versus compression, and how to combine space-time sampling with compression. My hopes are that these contributions will help further advance the global delivery of HFR video content.

Bio: Al Bovik is the Cockrell Family Regents Endowed Chair Professor at The University of Texas at Austin. His research interests land squarely at the nexus of visual neuroscience, deep learning, and digital streaming and social media. His many international honors include a 2020 Technology and Engineering Emmy® Award, the 2019 Progress Medal of the Royal Photographic Society, the 2019 IEEE Fourier Award, the 2017 OSA Edwin H. Land Medal, a 2015 Primetime Emmy® Award from the Academy of Television Arts and Sciences, and the Norbert Wiener and ‘Sustained Impact’ Awards of the IEEE Signal Processing Society.

Wangmeng Zuo

Harbin Institute of Technology

Title: Towards Guided and Generic Blind Face Restoration

Abstract: Blind restoration of unconstrained blurry, noisy, low-resolution, or compressed face images is a challenging low level vision task with many real-world applications such as faces in albums, old photos and old films, etc. While generic blind face restoration is difficult, we begin with a practically more feasible setting by exploiting both the degraded observation and a high-quality exemplar image for guided face restoration. Optical flow and moving least-square are subsequently introduced for spatial alignment of guidance image. And multiple adaptive spatial feature fusion is deployed to incorporate guidance features in an adaptive and progressive manner. By introducing generic dictionaries, we further extend adaptive spatial fusion for generic blind face restoration, and finally present a general framework for handling both generic and guided blind face restoration.

Bio: Wangmeng Zuo is currently a Professor in the School of Computer Science and Technology, Harbin Institute of Technology. He received the Ph.D. degree in computer application technology from the Harbin Institute of Technology, Harbin, China, in 2007. His current research interests include image enhancement and restoration, face image restoration and editing, object detection, visual tracking, and image classification. He has published over 100 papers in top tier academic journals and conferences. His publications have received 20,000+ citations in terms of Google Scholar. He has served as a Tutorial Organizer in ECCV 2016, an Associate Editor of IEEE Trans. Pattern Analysis and Machine Intelligence, and IEEE Trans. Image Processing.

Rakesh Ranjan, Federico Perazzi

Facebook Reality Labs

Title: Enhancing AR Camera using Deep learning

Abstract: AR Glasses promise to be the next compute platform, enabling a frictionless way of interacting with the world around us, by augmenting our perception of the real-world. They must be lightweight all day wearable devices, limiting the size of the sensors which can go into them as well as they must adhere to strict power and thermal limitations. In the first part of this talk we will present some of the constraints on camera imaging imposed by these limitations. In the second part we will present an efficient on-device neural network that employs a novel feature align layer and a perceptual loss computed in RAW space to achieve state-of-the-art results at a fraction of the computational cost.

Bio: Rakesh Ranjan is a Research Scientist Manager in Facebook Reality Labs. Rakesh and his team pursue research in the areas of AI based low-level Computer Vision and Graphics for Augmented and Virtual Reality devices. Prior to Facebook, Rakesh was a Research Scientist at Nvidia where he worked in the area of AI for Real Time Graphics (DLSS) and AI for Cloud Gaming (GeForce Now). Rakesh also spent 5 years at Intel Research as a PhD and full-time researcher.

Federico Perazzi is a Research Scientist On-Device AI team, at Facebook Reality Labs working on image enhancement vision tasks for the camera of the next-gen Facebook AR Glasses. Before joining Facebook, Federico was part of the Creative Intelligence Lab, at Adobe Research, where he co-authored several papers on the topic of denoising, generative models, and semantic image understanding. Federico spent eight years as Intern, Ph.D., and Post-Doctoral Researcher at Disney Research Zurich, in the Imaging and Video Processing Group. He obtained his Ph.D. in 2017 from ETHZ on the topic of video object segmentation.

Ayush Tewari, Christian Theobalt

MPI for Informatics, Saarland University

Title: Synthesis of Portrait Images with 3D Control

Abstract: Photorealistic and semantically controllable synthesis of portrait images has many applications in movies, virtual reality, and casual photography. Recent generative models, such as StyleGAN, have demonstrated high-quality synthesis of portrait images. However, they lack intuitive control over the 3D scene parameters. In this talk, I will cover some recent methods where we introduce controllability in pretrained generative models, allowing for high-quality as well as controllable synthesis of portrait images. I will describe how a pretrained generative model can offer a lot of advantages, especially in the presence of limited supervised training data.

Bio: Ayush Tewari is a Ph.D. student in the 'Visual Computing and Artificial Intelligence' department at the Max Planck Institute for Informatics in Saarbruecken, Germany. He received his M.Sc. in Computer Science from Grenoble INP, and B.Tech. in Computer Science and Engineering from IIIT Hyderabad. His research interests are in computer vision, computer graphics, and machine learning, with a focus on self-supervised 3D reconstruction and synthesis problems.

Christian Theobalt is a Professor of Computer Science and the head of the research group 'Graphics, Vision & Video' at the Max Planck Institute for Informatics, Saarbruecken, Germany. He is also a professor at Saarland University. His research lies on the boundary between Computer Vision and Computer Graphics. For instance, he works on 4D scene reconstruction, marker-less motion and performance capture, machine learning for graphics and vision, and new sensors for 3D acquisition. Christian received several awards, for instance the Otto Hahn Medal of the Max-Planck Society (2007), the EUROGRAPHICS Young Researcher Award (2009), the German Pattern Recognition Award (2012), an ERC Starting Grant (2013) and an ERC Consolidator Grant (2017). In 2015, he was elected one of Germany's top 40 innovators under 40 by the magazine Capital. He is a co-founder of theCaptury.

Qi Tian, Lin Liu

Huawei Cloud & AI

Title: Challenges and Solutions for Intelligent Image Restoration

Abstract: In recent years, with the development of deep learning, image restoration and enhancement, such as image denoising and image super-resolution, have attracted more and more attention. This talk will focus on the challenges faced by image restoration and propose some solutions: 1) For the problem that real data is difficult to obtain, we introduce methods of synthesizing more real data, self-supervised learning, and fine-tuning using pre-trained models. 2) For the existing models have limited in mining useful information, we first introduce the concept of ‘guidance restoration’, then introduce some self-guidance and external-guidance methods. 3) At last, we introduce some video or burst methods for image restoration.

Bio: Qi Tian is currently a Chief Scientist in Artificial Intelligence at Cloud BU, Huawei. From 2018-2020, he was the Chief Scientist in Computer Vision at Huawei Noah’s Ark Lab. Before that he was a Full Professor in the Department of Computer Science, the University of Texas at San Antonio (UTSA) from 2002 to 2019. During 2008-2009, he took one-year Faculty Leave at Microsoft Research Asia (MSRA).
Dr. Tian received his Ph.D. in ECE from University of Illinois at Urbana-Champaign (UIUC) and received his B.E. in Electronic Engineering from Tsinghua University and M.S. in ECE from Drexel University, respectively. Dr. Tian’s research interests include computer vision, multimedia information retrieval and machine learning and published 630+ refereed journal and conference papers. His Google citation is over 28500+ with H-index 81. He was the co-author of best papers including IEEE ICME 2019, ACM CIKM 2018, ACM ICMR 2015, PCM 2013, MMM 2013, ACM ICIMCS 2012, a Top 10% Paper Award in MMSP 2011, a Student Contest Paper in ICASSP 2006, and co-author of a Best Paper/Student Paper Candidate in ACM Multimedia 2019, ICME 2015 and PCM 2007.
Dr. Tian received 2017 UTSA President’s Distinguished Award for Research Achievement, 2016 UTSA Innovation Award, 2014 Research Achievement Awards from College of Science, UTSA, 2010 Google Faculty Award, and 2010 ACM Service Award. He is the associate editor of IEEE TMM, IEEE TCSVT, ACM TOMM, MMSJ, and in the Editorial Board of Journal of Multimedia (JMM) and Journal of MVA. Dr. Tian is the Guest Editor of IEEE TMM, Journal of CVIU, etc. Dr. Tian is a Fellow of IEEE(2016).
Lin Liu Lin Liu is a student in the Electronic Engineering and Information Science Department of University of Science and Technology of China (USTC). He received his Bachelor degree in the Information Security Department of University of Science and Technology of China in 2019. Previously, he spent 8 months at the Noah's Ark Lab, Huawei Tech as a research intern. His research interests are computer vision, machine learning and low-level vision.