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.
@article{arxiv.2604.09030,
title = {NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)},
author = {Lishen Qu and Yao Liu and Jie Liang and Hui Zeng and Wen Dai and Guanyi Qin and Ya-nan Guan and Shihao Zhou and Jufeng Yang and Lei Zhang and Radu Timofte and Xiyuan Yuan and Wanjie Sun and Shihang Li and Bo Zhang and Bin Chen and Jiannan Lin and Yuxu Chen and Qinquan Gao and Tong Tong and Song Gao and Jiacong Tang and Tao Hu and Xiaowen Ma and Qingsen Yan and Sunhan Xu and Juan Wang and Xinyu Sun and Lei Qi and He Xu and Jiachen Tu and Guoyi Xu and Yaoxin Jiang and Jiajia Liu and Yaokun Shi},
journal= {arXiv preprint arXiv:2604.09030},
year = {2026}
}