ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Aoyu, Liu, Zhen, Wang, Ziyi, Chen, Dian, Zeng, Bing, Liu, Shuaicheng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909011838763008
author Liu, Aoyu
Liu, Zhen
Wang, Ziyi
Chen, Dian
Zeng, Bing
Liu, Shuaicheng
author_facet Liu, Aoyu
Liu, Zhen
Wang, Ziyi
Chen, Dian
Zeng, Bing
Liu, Shuaicheng
contents Single-image HDR reconstruction aims to recover high dynamic range radiance from a single low dynamic range (LDR) input, but remains highly ill-posed due to detail saturation in over-exposed regions and noise amplification in under-exposed areas. While recent diffusion-based approaches offer powerful generative priors, they often overlook the exposure-dependent nature of the degradation and incur substantial computational costs from iterative sampling. To address these challenges, we propose ExpoCM, a novel one-step generative HDR reconstruction framework that reformulates HDR reconstruction as a Probability Flow ODE (PF-ODE) and constructs exposure-aware consistency trajectories via exposure-dependent perturbations. Specifically, a soft exposure mask is first constructed to separate the LDR image into over-, under-, and well-exposed regions. Based on this partition, region-conditioned consistency trajectories are designed to hallucinate saturated details, suppress noise in dark regions, and preserve reliable structures within a single, distillation-free inference step. To further enhance perceptual quality, we introduce an Exposure-guided Luminance-Chromaticity Loss in the CIE~$\text{L}^*\text{a}^*\text{b}^*$ space, which assigns exposure-aware weights to luminance and chromaticity components, effectively mitigating brightness bias and color drift. Extensive experiments on the HDR-REAL, HDR-EYE, and AIM2025 benchmarks demonstrate that ExpoCM achieves state-of-the-art fidelity and perceptual accuracy, while enabling over 400$\times$ and 20$\times$ faster inference compared to DDPM (1000 steps) and DDIM (50 steps), respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2605_02464
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction
Liu, Aoyu
Liu, Zhen
Wang, Ziyi
Chen, Dian
Zeng, Bing
Liu, Shuaicheng
Computer Vision and Pattern Recognition
Single-image HDR reconstruction aims to recover high dynamic range radiance from a single low dynamic range (LDR) input, but remains highly ill-posed due to detail saturation in over-exposed regions and noise amplification in under-exposed areas. While recent diffusion-based approaches offer powerful generative priors, they often overlook the exposure-dependent nature of the degradation and incur substantial computational costs from iterative sampling. To address these challenges, we propose ExpoCM, a novel one-step generative HDR reconstruction framework that reformulates HDR reconstruction as a Probability Flow ODE (PF-ODE) and constructs exposure-aware consistency trajectories via exposure-dependent perturbations. Specifically, a soft exposure mask is first constructed to separate the LDR image into over-, under-, and well-exposed regions. Based on this partition, region-conditioned consistency trajectories are designed to hallucinate saturated details, suppress noise in dark regions, and preserve reliable structures within a single, distillation-free inference step. To further enhance perceptual quality, we introduce an Exposure-guided Luminance-Chromaticity Loss in the CIE~$\text{L}^*\text{a}^*\text{b}^*$ space, which assigns exposure-aware weights to luminance and chromaticity components, effectively mitigating brightness bias and color drift. Extensive experiments on the HDR-REAL, HDR-EYE, and AIM2025 benchmarks demonstrate that ExpoCM achieves state-of-the-art fidelity and perceptual accuracy, while enabling over 400$\times$ and 20$\times$ faster inference compared to DDPM (1000 steps) and DDIM (50 steps), respectively.
title ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.02464