| Title | NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results |
| Authors | Yang, Ren Timofte, Radu Liu, Jing Xu, Yi Zhang, Xinjian Zhao, Minyi Zhou, Shuigeng Chan, Kelvin C. K. Zhou, Shangchen Xu, Xiangyu Loy, Chen Change Li, Xin Liu, Fanglong Zheng, He Jiang, Lielin Zhang, Qi He, Dongliang Li, Fu Dang, Qingqing Huang, Yibin Maggioni, Matteo Fu, Zhongqian Xiao, Shuai Li, Cheng Tanay, Thomas Song, Fenglong Chao, Wentao Guo, Qiang Liu, Yan Li, Jiang Qu, Xiaochao Hou, Dewang Yang, Jiayu Jiang, Lyn You, Di Zhang, Zhenyu Mou, Chong Koshelev, Iaroslav Ostyakov, Pavel Somov, Andrey Hao, Jia Zou, Xueyi Zhao, Shijie Sun, Xiaopeng Liao, Yiting Zhang, Yuanzhi Wang, Qing Zhan, Gen Guo, Mengxi Li, Junlin Lu, Ming Ma, Zhan Michelini, Pablo Navarrete Wang, Hai Chen, Yiyun Guo, Jingyu Zhang, Liliang Yang, Wenming Kim, Sijung Oh, Syehoon Wang, Yucong Cai, Minjie Hao, Wei Shi, Kangdi Li, Liangyan Chen, Jun Gao, Wei Liu, Wang Zhang, Xiaoyu Zhou, Linjie Lin, Sixin Wang, Ru |
| Affiliation | Swiss Fed Inst Technol, Comp Vis Lab, Zurich, Switzerland Bilibili Inc, Shanghai, Peoples R China Fudan Univ, Shanghai, Peoples R China Nanyang Technol Univ, S Lab, Singapore, Singapore Baidu Inc, Dept Comp Vis Technol VIS, Beijing, Peoples R China Huawei Technol Co Ltd, Huawei Noahs Ark Lab, Shenzhen, Peoples R China Meitu Inc, MTLab, Beijing, Peoples R China Peking Univ, Shenzhen, Peoples R China Tencent, Shenzhen, Peoples R China Skolkovo Inst Sci & Technol, Moscow, Russia Huawei Noahs Ark Lab, Shenzhen, Peoples R China HiSilicon Shanghai Technol CO LTD, Shanghai, Peoples R China ByteDance Ltd, Shenzhen, Peoples R China Nanjing Univ, Sch Elect Sci & Engn, Nanjing, Peoples R China BOE Technol Grp Co Ltd, Beijing, Peoples R China Tsinghua Univ, Shenzhen, Peoples R China SZ Da Jiang Innovat Sci & Technol Co Ltd, Shenzhen, Peoples R China Bluedot, Seoul, South Korea Hunan Univ, Coll Comp Sci & Elect Engn, Changsha, Peoples R China McMaster Univ, Hamilton, ON, Canada Peking Univ, Sch Elect & Comp Engn, Shenzhen Grad Sch, Shenzhen, Peoples R China Peng Cheng Lab, Shenzhen, Peoples R China |
| Issue Date | 2021 |
| Publisher | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021) |
| Abstract | This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with focus on proposed solutions and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, while Track 3 is designed for enhancing the videos compressed by x265 at a fixed bit-rate. Besides, the quality enhancement of Tracks 1 and 3 targets at improving the fidelity (PSNR), and Track 2 targets at enhancing the perceptual quality. The three tracks totally attract 482 registrations. In the test phase, 12 teams, 8 teams and 11 teams submitted the final results of Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement. The homepage of the challenge: https://github.com/RenYang-home/NTIRE21_VEnh |
| URI | http://hdl.handle.net/20.500.11897/628464 |
| ISBN | 978-1-6654-4899-4 |
| ISSN | 2160-7508 |
| DOI | 10.1109/CVPRW53098.2021.00075 |
| Indexed | CPCI-S(ISTP) |
| Appears in Collections: | 信息工程学院 |
