@inproceedings{ffb48e1585824cb796248908fd92e243,
title = "GMODiff: One-Step Gain Map Refinement with Diffusion Priors for Efficient HDR Reconstruction",
abstract = "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{\texttimes} faster than previous LDM-based methods.",
keywords = "Diffusion model, Gain map, HDR reconstruction",
author = "Tao Hu and Weiyu Zhou and Yanjie Tu and Wei Dong and Peng Wu and Qingsen Yan and Yanning Zhang",
note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; 19th European Conference on Computer Vision, ECCV 2026 ; Conference date: 08-09-2026 Through 12-09-2026",
year = "2026",
doi = "10.1007/978-3-032-37517-9\_31",
language = "英语",
isbn = "9783032375162",
series = "Lecture Notes in Computer Science",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "556--573",
editor = "Paolo Favaro and Zuzana Kukelova and Atsuto Maki and Anna Rohrbach and Konrad Schindler and Federico Tombari",
booktitle = "Computer Vision {\textendash} ECCV 2026 - 19th European Conference, 2026, Proceedings",
}