arXiv:2504.10686cs.CVeess.IV2025-04CVPR被引 36

244支队伍角逐高效超分辨率挑战,43支提交有效方案。

The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report

  • 聚焦计算效率,优化运行时、参数量和浮点运算次数。
  • 在DIV2K数据集上达到26.90~26.99 dB的峰值信噪比。
  • 为高效超分辨率研究提供新基准,适合模型压缩与部署者参考。

本文全面回顾了2025年NTIRE单图高效超分辨率(ESR)挑战赛。该挑战旨在推动深度模型在优化运行时间、参数量和浮点运算次数(FLOPs)的同时,于DIV2K_LSDIR_valid数据集上实现至少26.90 dB的峰值信噪比(PSNR),在DIV2K_LSDIR_test数据集上达到26.99 dB。共有244支队伍注册参赛,43支队伍提交了有效结果。本报告深入分析这些方法与性能,凸显单图高效超分辨率技术的前沿进展,提出创新性解决方案,并为未来研究建立基准。

原文摘要 · Abstract (English)

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 $\operatorname{DIV2K\_LSDIR\_valid}$ dataset and 26.99 dB on the $\operatorname{DIV2K\_LSDIR\_test}$ dataset. A robust participation saw \textbf{244} registered entrants, with \textbf{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.

超分辨率模型效率图像重建竞赛报告

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。