The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report

Abstract

This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution (ESR). The challenge aimed to advance the development of deep models that optimize key computational metrics, i.e., runtime, parameters, and FLOPs, while achieving a PSNR of at least 26.90 dB on the DIV2K_LSDIR_valid dataset and 26.99 dB on the DIV2K_LSDIR_test dataset. A robust participation saw 244 registered entrants, with 43 teams submitting valid entries. This report meticulously analyzes these methods and results, emphasizing groundbreaking advancements in state-of-the-art single-image ESR techniques. The analysis highlights innovative approaches and establishes benchmarks for future research in the field.

Cite

Text

Ren et al. "The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.

Markdown

[Ren et al. "The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/ren2025cvprw-tenth/)

BibTeX

@inproceedings{ren2025cvprw-tenth,
  title     = {{The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report}},
  author    = {Ren, Bin and Guo, Hang and Sun, Lei and Wu, Zongwei and Timofte, Radu and Li, Yawei},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2025},
  pages     = {917-966},
  url       = {https://mlanthology.org/cvprw/2025/ren2025cvprw-tenth/}
}