NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)

TL;DR

The paper introduces NTIRE 2026, a challenging benchmark and competition for multi-exposure image fusion in dynamic scenes, emphasizing real-world issues like motion and illumination changes.

Contribution

It provides a new dataset and evaluation framework for HDR image fusion in dynamic scenes, fostering advancements in artifact removal and detail recovery.

Findings

Winning methods significantly reduced ghosting artifacts.

Participants achieved improved PSNR, SSIM, and LPIPS scores.

The dataset and code are publicly available at the provided GitHub repository.

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.