NTIRE 2025图像超分辨率挑战赛，比拼×4放大效果的清晰度与真实感。
NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results
- 分重建与感知双赛道，分别以PSNR和视觉评分衡量性能。
- 25支队伍提交有效结果，涵盖多种网络设计与优化策略。
- 为图像超分辨率研究提供最新技术对比基准，适合领域研究者参考。
本文介绍了NTIRE 2025图像超分辨率（×4）挑战赛，作为CVPR 2025第十届NTIRE研讨会的关联竞赛之一。挑战目标是从通过双三次下采样生成的低分辨率（LR）图像中恢复高分辨率（HR）图像，比例为×4。旨在推动高效网络设计或解决方案的发展，以实现最先进的超分辨率性能。为体现图像超分辨率研究的双重目标，挑战赛包含两个子赛道：(1) 重建赛道，强调像素级精度，按PSNR排名；(2) 感知赛道，注重视觉真实感，按感知评分排名。共有286名参与者注册，25支团队提交有效参赛作品。本报告总结了挑战赛的设计、数据集、评估协议、主要结果及各团队方法。该挑战赛为推进技术前沿、促进图像超分辨率领域发展提供了重要基准。
原文摘要 · Abstract (English)
This paper presents the NTIRE 2025 image super-resolution ($\times$4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。