Name
Abstract | ||
|---|---|---|
This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of $\times$4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution. |
Year | Venue | DocType |
|---|---|---|
2022 | IEEE Conference on Computer Vision and Pattern Recognition | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
111 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yawei Li | 1 | 31 | 5.58 |
| Kai Zhang | 2 | 686 | 26.59 |
| Radu Timofte | 3 | 1880 | 118.45 |
| Luc Van Gool | 4 | 0 | 1.35 |
| Fangyuan Kong | 5 | 0 | 0.68 |
| Mingxi Li | 6 | 0 | 1.35 |
| Songwei Liu | 7 | 0 | 0.68 |
| Zongcai Du | 8 | 0 | 0.34 |
| Ding Liu | 9 | 611 | 32.97 |
| Chenhui Zhou | 10 | 0 | 0.34 |
| Jingyi Chen | 11 | 0 | 0.34 |
| Qingrui Han | 12 | 0 | 0.34 |
| Zheyuan Li | 13 | 0 | 0.68 |
| Yingqi Liu | 14 | 0 | 0.68 |
| Xiangyu Chen | 15 | 0 | 0.68 |
| Haoming Cai | 16 | 4 | 1.74 |
| Yu Qiao | 17 | 2267 | 152.01 |
| Chao Dong | 18 | 2064 | 80.72 |
| Long Sun | 19 | 1 | 1.09 |
| Jin-shan Pan | 20 | 567 | 30.84 |
| Yi Zhu | 21 | 0 | 0.34 |
| Zhikai Zong | 22 | 0 | 0.34 |
| Xiaoxiao Liu | 23 | 0 | 0.34 |
| Hui Zheng | 24 | 73 | 15.94 |
| Tao Yang | 25 | 160 | 76.32 |
| Peiran Ren | 26 | 162 | 11.58 |
| Xuansong Xie | 27 | 0 | 0.34 |
| Xian-Sheng Hua | 28 | 6566 | 328.17 |
| Yanbo Wang | 29 | 0 | 0.34 |
| Xiaozhong Ji | 30 | 3 | 2.06 |
| Chuming Lin | 31 | 9 | 4.14 |
| Donghao Luo | 32 | 3 | 2.42 |
| Ying Tai | 33 | 213 | 25.74 |
| Chengjie Wang | 34 | 43 | 19.03 |
| Zhizhong Zhang | 35 | 0 | 0.34 |
| Yuan Xie | 36 | 0 | 0.34 |
| Shen Cheng | 37 | 1 | 1.37 |
| Ziwei Luo | 38 | 5 | 1.75 |
| Lei Yu | 39 | 5 | 1.41 |
| Zhihong Wen | 40 | 0 | 0.68 |
| Qi Wu1 | 41 | 0 | 0.34 |
| Youwei Li | 42 | 5 | 2.09 |
| Haoqiang Fan | 43 | 8 | 3.13 |
| Jian Sun | 44 | 60 | 14.76 |
| Shuaicheng Liu | 45 | 363 | 28.26 |
| Yuanfei Huang | 46 | 0 | 0.34 |
| Meiguang Jin | 47 | 0 | 0.34 |
| Hua Huang | 48 | 803 | 62.97 |
| Jing Liu | 49 | 1781 | 88.09 |
| Xinjian Zhang | 50 | 0 | 0.34 |