AI RESEARCH
GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction
arXiv CS.CV
•
ArXi:2512.16357v2 Announce Type: replace 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