ExpoCM：曝光感知的单步生成式单图 HDR 重建
ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction
把单图 HDR 重建重构成概率流 ODE 并用曝光分区构造区域条件一致性轨迹，实现免蒸馏单步推理；这套「软曝光掩码 + 区域条件轨迹」思路可直接迁移到去噪、低光照增强、去模糊等退化随空间位置变化的复原任务，同时其 CIE Lab 空间的亮度-色度加权损失可缓解生成式复原常见的亮度偏置与色偏。
原文依据 constructs exposure-aware consistency trajectories via exposure-dependent perturbations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单图 HDR 重建旨在从单张低动态范围（LDR）输入中恢复高动态范围辐亮度，但由于过曝区域的细节饱和与欠曝区域的噪声放大，该问题仍高度病态。尽管近期基于扩散的方法提供了强大的生成先验，但它们往往忽略了退化对曝光的依赖性，并因迭代采样而带来可观的计算开销。为应对这些挑战，我们提出 ExpoCM，一种新颖的单步生成式 HDR 重建框架，它将 HDR 重建重新表述为概率流 ODE（PF-ODE），并通过依赖曝光的扰动构造曝光感知的一致性轨迹。具体而言，首先构造软曝光掩码，将 LDR 图像划分为过曝、欠曝与曝光良好区域。基于该划分，设计区域条件的一致性轨迹，在单个免蒸馏的推理步内幻觉出饱和细节、抑制暗区噪声并保留可靠结构。为进一步提升感知质量，我们引入 CIE L*a*b* 空间中的曝光引导亮度-色度损失，对亮度与色度分量赋予曝光感知权重，有效缓解亮度偏置与颜色漂移。在 HDR-REAL、HDR-EYE 与 AIM2025 基准上的大量实验表明，ExpoCM 达到了最优的保真度与感知准确度，同时相比 DDPM（1000 步）与 DDIM（50 步）分别实现超过 400 倍与 20 倍的推理加速。代码见 https://github.com/AoyuLiu01/ExpoCM。
英文原文摘要 1695 字符
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 400xand 20xfaster inference compared to DDPM (1000 steps) and DDIM (50 steps), respectively. Code is available at https://github.com/AoyuLiu01/ExpoCM.