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

TL;DR

ExpoCM introduces a one-step, exposure-aware HDR reconstruction method reformulating the task as a PF-ODE, achieving state-of-the-art results with significantly faster inference.

Contribution

It presents a novel exposure-aware, one-step generative HDR reconstruction framework using a PF-ODE formulation and exposure-dependent perturbations, without requiring distillation.

Findings

Achieves state-of-the-art fidelity and perceptual accuracy on multiple benchmarks.

Over 400x faster than DDPM and 20x faster than DDIM inference.

Effectively reconstructs details in over- and under-exposed regions.

Abstract

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.