ML Anthology

AIM 2019 Challenge on Video Extreme Super-Resolution: Methods and Results

Dario Fuoli, Xiaoyong Shen, Shutao Xia, Yurong Dai, Jiaya Jia, Peng Yi, Zhongyuan Wang, Kui Jiang, Junjun Jiang, Jiayi Ma, Zhiwei Zhong, Shuhang Gu, Chenyang Wang, Junjun Jiang, Xianming Liu, Radu Timofte, Xin Tao, Wenbo Li, Taian Guo, Zijun Deng, Liying Lu, Tao Dai
ICCVW 2019 pp. 3467-3475
doi:10.1109/ICCVW.2019.00430 /iccvw/2019/fuoli2019iccvw-aim/

Abstract

This paper reviews the extreme video super-resolution challenge from the AIM 2019 workshop, with emphasis on submitted solutions and results. Video extreme super-resolution x16 is a highly challenging problem, because 256 pixels need to be estimated for each single pixel in the low-resolution (LR) input. Contrary to single image super-resolution (SISR), video provides temporal information, which can be additionally leveraged to restore the heavily downscaled videos and is imperative for any video super-resolution (VSR) method. The challenge is composed of two tracks, to find the best performing method for fully supervised VSR (track 1) and to find the solution which generates the perceptually best looking outputs (track 2). A new video dataset, called Vid3oC, is introduced together with the challenge.

PDF ICCVW Semantic Scholar

Cite

Text

Fuoli et al. "AIM 2019 Challenge on Video Extreme Super-Resolution: Methods and Results." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00430

Markdown

[Fuoli et al. "AIM 2019 Challenge on Video Extreme Super-Resolution: Methods and Results." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/fuoli2019iccvw-aim/) doi:10.1109/ICCVW.2019.00430

BibTeX

@inproceedings{fuoli2019iccvw-aim,
  title     = {{AIM 2019 Challenge on Video Extreme Super-Resolution: Methods and Results}},
  author    = {Fuoli, Dario and Shen, Xiaoyong and Xia, Shutao and Dai, Yurong and Jia, Jiaya and Yi, Peng and Wang, Zhongyuan and Jiang, Kui and Jiang, Junjun and Ma, Jiayi and Zhong, Zhiwei and Gu, Shuhang and Wang, Chenyang and Jiang, Junjun and Liu, Xianming and Timofte, Radu and Tao, Xin and Li, Wenbo and Guo, Taian and Deng, Zijun and Lu, Liying and Dai, Tao},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {3467-3475},
  doi       = {10.1109/ICCVW.2019.00430},
  url       = {https://mlanthology.org/iccvw/2019/fuoli2019iccvw-aim/}
}