NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results

Goutam Bhat, Martin Danelljan, Radu Timofte

CVPRW 2021 pp. 613-626

doi:10.1109/CVPRW53098.2021.00073 /cvprw/2021/bhat2021cvprw-ntire/

Abstract

This paper reviews the NTIRE2021 challenge on burst super-resolution. Given a RAW noisy burst as input, the task in the challenge was to generate a clean RGB image with 4 times higher resolution. The challenge contained two tracks; Track 1 evaluating on synthetically generated data, and Track 2 using real-world bursts from mobile camera. In the final testing phase, 6 teams submitted results using a diverse set of solutions. The top-performing methods set a new state-of-the-art for the burst super-resolution task.

PDF CVPRW Semantic Scholar

Cite

Text

Bhat et al. "NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00073

Markdown

[Bhat et al. "NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/bhat2021cvprw-ntire/) doi:10.1109/CVPRW53098.2021.00073

BibTeX

@inproceedings{bhat2021cvprw-ntire,
  title     = {{NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results}},
  author    = {Bhat, Goutam and Danelljan, Martin and Timofte, Radu},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {613-626},
  doi       = {10.1109/CVPRW53098.2021.00073},
  url       = {https://mlanthology.org/cvprw/2021/bhat2021cvprw-ntire/}
}