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

• URL: http://arxiv.org/abs/2604.09030v1
• Date: Fri, 10 Apr 2026 06:47:42 GMT
• Title: NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)
• Abstract summary: This paper presents NTIRE 2026, the 3rd Restore Any Image Model (RAIM) challenge on multi-exposure image fusion in dynamic scenes.<n>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.<n>The winning methods significantly improved the ability to remove artifacts from multi-exposure fusion and recover fine details.
• Score: 82.64620983570866
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3) [127.69044386248355]
  We present a comprehensive overview of the NTIRE 2026 3rd Restore Any Image Model (RAIM) challenge.<n>This challenge aims to establish a novel benchmark for real-world low-light portrait restoration.<n>This report details the motivation behind the challenge, the dataset construction process, the evaluation metrics, and the various phases of the competition.
  arXiv  Detail & Related papers  (2026-04-13T09:30:56Z)
• NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods [99.67550064860554]
  We review the NTIRE 2026 challenge on single-image reflection removal (SIRR) in the wild.<n>This dataset requires participants to process real-world images covering a range of reflection scenarios and intensities.<n>The top-ranked methods advanced the state-of-the-art reflection removal performance and earned unanimous recognition from five experts in the field.
  arXiv  Detail & Related papers  (2026-04-11T19:03:03Z)
• NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challenge [60.38046597325693]
  The NTIRE 2025 challenge established a new benchmark for real-world image restoration.<n>The challenge attracted nearly 300 registrations, with 51 teams submitting more than 600 results.<n>The top-performing methods advanced the state of the art in image restoration and received unanimous recognition from all 20+ expert judges.
  arXiv  Detail & Related papers  (2025-06-02T07:43:35Z)
• AIM 2024 Sparse Neural Rendering Challenge: Methods and Results [64.19942455360068]
  This paper reviews the challenge on Sparse Neural Rendering that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. The challenge aims at producing novel camera view synthesis of diverse scenes from sparse image observations. Participants are asked to optimise objective fidelity to the ground-truth images as measured via the Peak Signal-to-Noise Ratio (PSNR) metric.
  arXiv  Detail & Related papers  (2024-09-23T14:17:40Z)
• Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes [58.66427721308464]
  Self is a self-supervised reconstruction method that only requires dynamic multi-exposure images during training. Self achieves superior results against the state-of-the-art self-supervised methods, and comparable performance to supervised ones.
  arXiv  Detail & Related papers  (2023-10-03T07:10:49Z)
• NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results [173.32437855731752]
  The challenge was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022. The challenge aims at estimating an HDR image from multiple respective low dynamic range (LDR) observations.
  arXiv  Detail & Related papers  (2022-05-25T10:20:06Z)
• Self-supervised HDR Imaging from Motion and Exposure Cues [14.57046548797279]
  We propose a novel self-supervised approach for learnable HDR estimation that alleviates the need for HDR ground-truth labels. Experimental results show that the HDR models trained using our proposed self-supervision approach achieve performance competitive with those trained under full supervision.
  arXiv  Detail & Related papers  (2022-03-23T10:22:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.