NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)
2026-04-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors organized the NTIRE 2026 challenge to improve how computers combine several pictures taken at different light levels into one clear image, even when things in the scene move or the camera shakes. They created a special test set with real-world conditions that often cause blurry or fuzzy areas in the combined images. Many teams competed by submitting methods judged on quality, speed, and how well they could be copied by others. The winning approaches better removed unwanted artifacts and kept fine image details. The authors also shared the dataset and participants' code publicly for further research.
multi-exposure image fusionHDR imagingexposure bracketingscene motionimage misalignmentghosting artifactsPSNRSSIMLPIPSperceptual quality
Authors
Lishen Qu, Yao Liu, Jie Liang, Hui Zeng, Wen Dai, Guanyi Qin, Ya-nan Guan, Shihao Zhou, Jufeng Yang, Lei Zhang, Radu Timofte, Xiyuan Yuan, Wanjie Sun, Shihang Li, Bo Zhang, Bin Chen, Jiannan Lin, Yuxu Chen, Qinquan Gao, Tong Tong, Song Gao, Jiacong Tang, Tao Hu, Xiaowen Ma, Qingsen Yan, Sunhan Xu, Juan Wang, Xinyu Sun, Lei Qi, He Xu, Jiachen Tu, Guoyi Xu, Yaoxin Jiang, Jiajia Liu, Yaokun Shi
Abstract
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.