NTIRE 2026 第三次恢复任何图像模型（RAIM）挑战：动态场景中的多曝光图像融合（Track 2）
NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)
AI总结：
本文提出NTIRE 2026挑战，针对动态场景中多曝光图像融合的HDR成像难题，提供包含100训练序列和100测试序列的基准数据集，评估PSNR、SSIM、LPIPS等指标及感知质量，最终由114支队伍提交987份方案，提升去噪和细节恢复能力。
摘要：
本文介绍了NTIRE 2026，即第三次恢复任何图像模型（RAIM）挑战，聚焦于动态场景中的多曝光图像融合。我们引入了一个针对实际但困难的HDR成像设置的基准，其中必须在场景运动、光照变化和手持相机抖动的情况下进行曝光拼接。挑战数据集包含100个训练序列（7个曝光级别）和100个测试序列（5个曝光级别），反映了现实场景中常导致对齐错误和鬼影伪影的情况。我们通过PSNR、SSIM和LPIPS导出的排行榜分数评估提交方案，同时考虑感知质量、效率和可重复性。该赛道吸引了114支参赛队伍，共收到987份提交。获胜方法显著提升了从多曝光融合中去除伪影和恢复细节的能力。数据集和各团队代码可在仓库：https://github.com/qulishen/RAIM-HDR 中找到。
英文摘要：
This paper presents NTIRE 2026, the 3rd Restore Any Image Model (RAIM) challenge on multi-exposure image fusion in dynamic scenes. We introduce a benchmark that targets a practical yet difficult HDR imaging setting, where exposure bracketing must be fused under scene motion, illumination variation, and handheld camera jitter. The challenge data contains 100 training sequences with 7 exposure levels and 100 test sequences with 5 exposure levels, reflecting real-world scenarios that frequently cause misalignment and ghosting artefacts. We evaluate submissions with a leaderboard score derived from PSNR, SSIM, and LPIPS, while also considering perceptual quality, efficiency, and reproducibility during the final review. This track attracted 114 participating teams and received 987 submissions. The winning methods significantly improved the ability to remove artifacts from multi-exposure fusion and recover fine details. The dataset and the code of each team can be found at the repository: https://github.com/qulishen/RAIM-HDR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
