跳到主要导航 跳到搜索 跳到主要内容

GMODiff: One-Step Gain Map Refinement with Diffusion Priors for Efficient HDR Reconstruction

  • Northwestern Polytechnical University Xian
  • Xi'an University of Architecture and Technology

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Pre-trained Latent Diffusion Models (LDMs) have recently shown strong perceptual priors for low-level vision tasks, making them a promising direction for multi-exposure High Dynamic Range (HDR) reconstruction. However, directly applying LDMs to HDR remains challenging due to: (1) limited dynamic-range representation caused by 8-bit latent compression, (2) high inference cost from multi-step denoising, and (3) content hallucination inherent to generative nature. To address these challenges, we introduce GMODiff, a gain map-driven one-step diffusion framework for multi-exposure HDR reconstruction. Instead of reconstructing full HDR content, we reformulate HDR reconstruction as a degradation-aware Gain Map (GM) refinement problem, where the GM encodes the extended dynamic range while retaining the same bit depth as LDR images. We initialize the denoising process from an informative regression-based estimate rather than pure noise, allowing the model to generate high-quality GMs in a single denoising step. Furthermore, recognizing that regression-based models excel in content fidelity while LDMs favor perceptual quality, we leverage regression priors to guide both the denoising process and latent decoding of the LDM, suppressing hallucinations while preserving structural accuracy. Extensive experiments demonstrate that our GMODiff performs favorably against several state-of-the-art methods and is 100× faster than previous LDM-based methods.

源语言英语
主期刊名Computer Vision – ECCV 2026 - 19th European Conference, 2026, Proceedings
编辑Paolo Favaro, Zuzana Kukelova, Atsuto Maki, Anna Rohrbach, Konrad Schindler, Federico Tombari
出版商Springer Science and Business Media Deutschland GmbH
页556-573
页数18
ISBN(印刷版)9783032375162
DOI
出版状态已出版 - 2026
活动19th European Conference on Computer Vision, ECCV 2026 - Malmö, 瑞典
期限: 8 9月 2026 → 12 9月 2026

丛书

姓名Lecture Notes in Computer Science
卷17018 LNCS
ISSN(印刷版)0302-9743
ISSN(电子版)1611-3349

会议

会议19th European Conference on Computer Vision, ECCV 2026
国家/地区瑞典
市Malmö
时期8/09/26 → 12/09/26

学术指纹

探究 'GMODiff: One-Step Gain Map Refinement with Diffusion Priors for Efficient HDR Reconstruction' 的科研主题。它们共同构成独一无二的学术指纹。

引用此