国际影响力
全球前2%顶尖科学家
AI 2000人工智能全球最具影响力学者
入选2023年“中国高被引学者”榜单(Elsevier发布)
所获荣誉
2023年上海市技术发明奖一等奖
在PIRM 2018、NTIRE 2019、AIM 2020、NTIRE 2021、NTIRE 2022等国挑战赛中获得9项冠军
科研成果
基于无监督学习与多帧自相似性的视频盲超分辨率核心算法研究,国家自然科学基金面上项目,2022.10-2026.12,主持
[1]Wenlong Zhang, Xiaohui Li, Xiangyu Chen, Yu Qiao, Xiao-Ming Wu, Chao Dong. “SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution”. International Conference on Learning Representations (ICLR spotlight), 2024.
[2]Yihao Liu, Hengyuan Zhao, Jinjin Gu, Yu Qiao, Chao Dong. “Evaluating the Generalization Ability of Super-Resolution Networks”. IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2023.(IF=23.6)
[3]Wenlong Zhang, Xiaohui Li, Guangyuan Shi, Xiangyu Chen, Yu Qiao, Xiao-Ming Wu, Chao Dong. “Real-World Image Super-Resolution as Multi-Task Learning”. Conference and Workshop on Neural Information Processing Systems(NeurIPS), 2023.
[4]Jinjin Gu, Xianzheng Ma, Xiangtao Kong, Yu Qiao, Chao Dong. “Networks are Slacking Off: Understanding Generalization Problem in Image Deraining”. Conference and Workshop on Neural Information Processing Systems(NeurIPS), 2023.
[5]Yihao Liu, Jingwen He, Jinjin Gu, Xiangtao Kong, Yu Qiao, Chao Dong. “DegAE: A New Pretraining Paradigm for Low-level Vision”. Computer Vision and Pattern Recognition (CVPR highlight), 2023.
[6]Xiangyu Chen, Xintao Wang, Jiantao Zhou, Yu Qiao, Chao Dong. “Activating More Pixels in Image Super-Resolution Transformer”. Computer Vision and Pattern Recognition (CVPR), 2023.
[7]Fanghua Yu, Xintao Wang, Mingdeng Cao, Gen Li, Ying Shan, Chao Dong. “OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer”. Computer Vision and Pattern Recognition (CVPR), 2023
[8]Shuwei Shi, Jinjin Gu, Liangbin Xie, Xintao Wang, Yujiu Yang, Chao Dong. “Rethinking Alignment in Video Super-Resolution Transformers”. Conference and Workshop on Neural Information Processing Systems(NeurIPS), 2022.
[9]Anran Liu, Yihao Liu, Jinjin Gu, Yu Qiao, Chao Dong. “Blind Image Super-Resolution: A Survey and Beyond”. IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2022.(IF=23.6)
[10]Yihao Liu, Jingwen He, Xiangyu Chen, Zhengwen Zhang, Hengyuan Zhao, Chao Dong, Yu Qiao. “Very Lightweight Photo Retouching Network with Conditional Sequential Modulation”. IEEE Transactions on Multimedia (TMM), 2022.
[11]Xiangtao Kong, Xina Liu, Jinjin Gu, Yu Qiao, Chao Dong. “Reflash Dropout in Image Super-Resolution”. Computer Vision and Pattern Recognition (CVPR), 2022.
[12]Jingwen He, Wu Shi, Kai Chen, Lean Fu, Chao Dong. “GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors”. Computer Vision and Pattern Recognition (CVPR), 2022.
[13]Liangbin Xie, Xintao Wang, Chao Dong, Zhongang Qi, Ying Shan. “Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution”. Conference and Workshop on Neural Information Processing Systems (NeurIPS Spotlight), 2021.
[14]Jingwen He, Chao Dong, Liu Yihao, Yu Qiao. “Interactive Multi-Dimension Modulation for Image Restoration”. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.(IF=23.6)
[15]Wenlong Zhang, Yihao Liu, Chao Dong, Yu Qiao. “RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank”. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.(IF=23.6)
[16]Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, Chen Change Loy. ”Esrgan: Enhanced super-resolution generative adversarial networks”. the European conference on computer vision (ECCV) workshops, 2018.(谷歌学术引用量4149)
[17]Chao Dong, Chen Change Loy, Xiaoou Tang. “Accelerating the super-resolution convolutional neural network”. the European conference on computer vision (ECCV), 2016.(谷歌学术引用量3612)
[18]Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang. “Image super-resolution using deep convolutional networks”. IEEE transactions on pattern analysis and machine intelligence(TPAMI), 2015.(谷歌学术引用量9506)
[19]Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang. “Learning a deep convolutional network for image super-resolution”. the European conference on computer vision (ECCV), 2014.(谷歌学术引用量6507)
成果转化情况:与上海交通大学、华为、咪咕视频合作,开发了基于先验自适应的视频超分算法,实现了对上世纪40-80年代超低分辨率视频的超分辨增强,被应用于中央广播电视总台、咪咕视讯、云视科技等龙业企头,支撑了229部影视经典和279段珍贵历史资料的超高清增强任务。其中,所复原的《开国大典》视频片段在央视建党百年庆典晚会上,用12x4k超大显示屏进行现场播放。中共一大纪念馆中的所有视频均通过该算法进行增强。联合申请的项目《真实世界视频智能增强技术及国产化应用》获得了2023年的上海市技术发明一等奖。