AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
- Zhang K.
- Danelljan M.
- Li Y.
- Timofte R.
- Liu J.
- Tang J.
- Wu G.
- Zhu Y.
- He X.
- Xu W.
- Li C.
- Leng C.
- Cheng J.
- Wu G.
- Wang W.
- Liu X.
- Zhao H.
- Kong X.
- He J.
- Qiao Y.
- Dong C.
- Luo X.
- Chen L.
- Zhang J.
- Suin M.
- Purohit K.
- Rajagopalan A. N.
- Li X.
- Lang Z.
- Nie J.
- Wei W.
- Zhang L.
- Muqeet A.
- Hwang J.
- Yang S.
- Kang J. H.
- Bae S. -H.
- Kim Y.
- Qu Y.
- Jeon G. -W.
- Choi J. -H.
- Kim J. -H.
- Lee J. -S.
- Marty S.
- Marty E.
- Xiong D.
- Chen S.
- Zha L.
- Jiang J.
- Gao X.
- Lu W.
- Wang H.
- Bhaskara V.
- Levinshtein A.
- Tsogkas S.
- Jepson A.
- Kong X.
- Zhao T.
- Zhao S.
- Hrishikesh P. S.
- Puthussery D.
- Jiji C. V.
- Nan N.
- Liu S.
- Cai J.
- Meng Z.
- Ding J.
- Ho C. M.
- Wang X.
- Yan Q.
- Zhao Y.
- Chen L.
- Sun L.
- Wang W.
- Liu Z.
- Lan R.
- Umer R. M.
- Micheloni C.
Publication date
January 2020
DOI Publisher
Springer Science and Business Media LLCAbstract
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor × 4 based on a set of prior examples of low and corresponding high resolution images. The goal is to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption while at least maintaining PSNR of MSRResNet. The track had 150 registered participants, and 25 teams submitted the final results. They gauge the state-of-the-art in efficient single image super-resolution
Add to ORKG