We propose a novel framework to generate clean video frames from a single motion-blurred image. While a broad range of literature focuses on recovering a single image from a blurred image, in this work, we tackle a more challenging task i.e. video restoration from a blurred image. We formulate video restoration from a single blurred image as an inverse problem by setting clean image sequence and their respective motion as latent factors, and the blurred image as an observation. Our framework is based on an encoder-decoder structure with spatial transformer network modules to restore a video sequence and its underlying motion in an end-to-end manner. We design a loss function and regularizers with complementary properties to stabilize the training and analyze variant models of the proposed network. The effectiveness and transferability of our network are highlighted through a large set of experiments on two different types of datasets: camera rotation blurs generated from panorama scenes and dynamic motion blurs in high speed videos.
Blur-Attention: A boosting mechanism for non-uniform blurred image restoration
Beijing University of Technology（北京工业大学）；Beijing Key Laboratory of Computational Intelligence and Intelligent System（计算智能与智能系统北京市重点实验室）；The Hong Kong Polytechnic University（香港理工大学）
Hybrid CNN-ViT Framework for Motion-Blurred Scene Text Restoration
Department of Electrical Engineering, University of Engineering & Technology, New Campus, Lahore, Pakistan（电子工程系，工程科技大学，新校区，拉合尔，巴基斯坦）；Department of Electrical, Electronic, and Future Technologies, Sheffield Hallam University, Sheffield S1 1WB, UK（电子、电气与未来技术系，谢菲尔德哈姆大学，谢菲尔德 S1 1WB，英国）
A Constrained Deformable Convolutional Network for Efficient Single Image Dynamic Scene Blind Deblurring with Spatially-Variant Motion Blur Kernels Estimation
Chongqing University of Posts and Telecommunications（重庆邮电大学）；Chongqing University（重庆大学）
FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred Videos
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心（BNRist））；SenseTime Research（商汤科技研究院）；Amazon Rekognition（亚马逊Rekognition）
AstroClearNet: Deep image prior for multi-frame astronomical image restoration
Department of Applied Mathematics and Statistics, Johns Hopkins University（应用数学与统计学系，约翰霍普金斯大学）；Johns Hopkins University（约翰霍普金斯大学）；Department of Computer Science, Johns Hopkins University（计算机科学系，约翰霍普金斯大学）；Department of Physics and Astronomy, Johns Hopkins University（物理与天文学系，约翰霍普金斯大学）
RetinaRegen: A Hybrid Model for Readability and Detail Restoration in Fundus Images
Sichuan University（四川大学）；International School,Beijing University of Posts and Telecommunications（北京邮电大学国际学院）；School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）
The ADAPT SFI Research Centre（ADAPT SFI研究中心）；University College Dublin（都柏林大学）；Ram Lal Anand College, University of Delhi（德里大学Ram Lal Anand学院）；Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）
MoTDiff: High-resolution Motion Trajectory estimation from a single blurred image using Diffusion models
Department of Artificial Intelligence (AI), Sungkyunkwan University (SKKU)（人工智能系，全北国立大学）；Department of Electrical and Computer Engineering (ECE), SKKU（电气电子工程系，全北国立大学）；New Technology Team, ALLforLAND Co., Ltd.（ALLforLAND公司新技术团队）；Department of ECE, SKKU（电气电子工程系，全北国立大学）；Departments of AI, ECE, Semiconductor Convergence Engineering, Advanced Display Engineering, and Display Convergence Engineering, SKKU（人工智能系、电气电子工程系、半导体融合工程系、先进显示工程系和显示融合工程系，全北国立大学）；Center for Neuroscience Imaging Research, Institute for Basic Science, Suwon（神经科学成像研究中心，基础科学研究所）
DeblurNVS: Geometric Latent Diffusion for Novel View Synthesis from Sparse Motion-Blurred Images
School of AI for Science, Peking University Shenzhen Graduate School（人工智能科学学院，北京大学深圳研究生院）；School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School（电子与计算机工程学院，北京大学深圳研究生院）
Deblur-Avatar: Animatable Avatars from Motion-Blurred Monocular Videos
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）；S-Lab for Advanced Intelligence, Nanyang Technological University（南洋理工大学先进智能实验室）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；SenseTime Research（商汤科技研究院）
An Adaptive Edge-Guided Dual-Network Framework for Fast QR Code Motion Deblurring
Guangdong Provincial Key Lab of Robotics and Intelligent Systems（广东省机器人与智能系统重点实验室）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Nano Science and Technology, University of Science and Technology of China（中国科学技术大学纳米科学与技术学院）；Shenzhen University of Advanced Technology（深圳大学）
Leveraging Classic Deconvolution and Feature Extraction in Zero-Shot Image Restoration
Technical University of Munich（慕尼黑工业大学）；Helmholtz AI, Helmholtz Munich - German Research Center for Environmental Health（亥姆霍兹人工智能平台，亥姆霍兹慕尼黑中心——德国环境健康研究中心）；Georg-August-University Göttingen（哥廷根乔治-奥古斯特大学）；GEOMAR Helmholtz Centre for Ocean Research Kiel（基尔亥姆霍兹海洋研究中心）
Southwest Jiaotong University（西南交通大学）；Nanyang Technological University（南洋理工大学）；Tongji University（同济大学）；National University of Singapore（新加坡国立大学）；Tsinghua University（清华大学）
TextIR: A Simple Framework for Text-based Editable Image Restoration
Tsinghua University（清华大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shanghai AI Laboratory（上海人工智能实验室）；Peng Cheng Laboratory（鹏城实验室）
