This paper reviews the AIM 2019 challenge on constrained example-based single image super-resolution with focus on proposed solutions and results. The challenge had 3 tracks. Taking the three main aspects (i.e., number of parameters, inference/running time, fidelity (PSNR)) of MSRResNet as the baseline, Track 1 aims to reduce the amount of parameters while being constrained to maintain or improve the running time and the PSNR result, Tracks 2 and 3 aim to optimize running time and PSNR result with constrain of the other two aspects, respectively. Each track had an average of 64 registered participants, and 12 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.
Cite
@article{arxiv.1911.01249,
title = {AIM 2019 Challenge on Constrained Super-Resolution: Methods and Results},
author = {Kai Zhang and Shuhang Gu and Radu Timofte and Zheng Hui and Xiumei Wang and Xinbo Gao and Dongliang Xiong and Shuai Liu and Ruipeng Gang and Nan Nan and Chenghua Li and Xueyi Zou and Ning Kang and Zhan Wang and Hang Xu and Chaofeng Wang and Zheng Li and Linlin Wang and Jun Shi and Wenyu Sun and Zhiqiang Lang and Jiangtao Nie and Wei Wei and Lei Zhang and Yazhe Niu and Peijin Zhuo and Xiangzhen Kong and Long Sun and Wenhao Wang},
journal= {arXiv preprint arXiv:1911.01249},
year = {2019}
}