CVPR2025

LEDiff: Latent Exposure Diffusion for HDR Generation

Chao Wang, Zhihao Xia, Thomas Leimkühler, Karol Myszkowski, Xuaner Zhang

摘要

A wine glass on a wooden surface, illuminated by a warm light, creating re!ections and shadows" generated from Stable Di"usion. (b) a real photo with over-exposure (c) a real photo with under-exposure (#) LEDi" output (e) LEDi" output (d) LEDi" output Figure 1. LEDiff enables high dynamic range (HDR) content generation with photorealistic details in both over-and under-exposed regions by performing exposure fusion in latent space, making it applicable to generated content and real photos mapped to the latent space. While existing generative models (e.g., Stable Diffusion) are restricted to low dynamic range (a) and standard cameras struggle to capture full scene dynamic range, causing clipping in highlights (b) and shadows (c), LEDiff restores both detail and dynamic range (d)-(f), as shown in scanline plots. All HDR images are tone-mapped for visualization and are best viewed on an HDR display. See the supplemental for more details.