NTIRE 2026低光照增强：Twilight Cowboy挑战赛
NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge
浏览论文内容
中文总结 AI 辅助
本文综述NTIRE 2026低光照增强挑战赛，其旨在合并低光照下未对齐智能手机图像，采用585场景数据集与三阶段评估，10支队伍超基线，PSNR最高升6.49dB、SSIM升0.0101，获burst低光照增强新SOTA。
中文摘要 AI 辅助
本文对NTIRE 2026低光照增强：Twilight Cowboy挑战赛进行了综述。该竞赛的目标是将低光照条件下在原始域中捕获的一组未对齐的智能手机图像合并为一张清晰的图像。竞赛设置同时解决了低光照摄影的两个问题：高噪声和混合场景光源等视觉退化，以及多帧捕获期间手部移动导致的几何不一致。为推进低光照和夜间计算摄影的研究，研究人员收集了包含585个真实场景的具有挑战性的数据集，涵盖室内低光照和室外夜间条件，用于训练和基准测试参赛方案。竞赛采用三阶段评估方案：第一和第二阶段通过CodaBench平台进行自动验证，最终排名则在私有测试集上进行盲评。共有10支队伍超过了既定基线，在峰值信噪比（PSNR）上实现了高达+6.49 dB的提升，结构相似性指数（SSIM）上提升了+0.0101，从而为基于burst的低光照图像增强建立了新的最先进性能。这些结果表明在处理低光照场景中的真实噪声、运动和光照变化方面取得了显著进展。全面结果、排行榜及其他信息可在该https URL公开获取。
英文摘要
This paper presents a review of the NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge. The objective of the competition was to merge a set of misaligned smartphone images in the raw domain, captured in low-light conditions, into a single, clean image. Introduced setup simultaneously addresses two problems of low-light photography: visual degradations such as high noise and mixed scene illuminants, and the geometric inconsistencies caused by hand movement during multi-frame capture. To advance research in low-light and nighttime computational photography, a challenging dataset was collected comprising 585 real-world scenes, spanning indoor low-light and outdoor nighttime conditions, for training and benchmarking participant solutions. The competition employed a three-stage evaluation protocol: automatic validation via the CodaBench platform in stages one and two, followed by blind assessment on a private test set for the final ranking. Ten teams surpassed the established baseline, achieving improvements of up to +6.49 dB in PSNR and +0.0101 in SSIM, thereby establishing new state-of-the-art performance for burst-based low-light image enhancement. These results demonstrate significant progress in handling real-world noise, motion, and illumination variability in the low-light setting. Comprehensive results, leaderboards, and additional information are publicly available at https://nightimaging.org.
