LEDiff: Latent Exposure Diffusion for HDR Generation
Chao Wang, Zhihao Xia, Thomas Leimkühler, Karol Myszkowski, Xuaner Zhang
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext d4465629-8193-4065-bc90-390ef179aa93Cited by top-tier papers8
- GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDRChristophe Bolduc, Yannick Hold-Geoffroy, Jean-François LalondeICCV 2025 · 14 citations
- HDR Image Generation via Gain Map Decomposed DiffusionYuanshen Guan, Ruikang Xu, Yinuo Liao, Mingde Yao et al.ICCV 2025 · 1 citation
- VENI: Variational Encoder for Natural IlluminationPaul Walker, James A. D. Gardner, Andreea Ardelean, William A. P. Smith et al.CVPR 2026 · 1 citation
- Physically Inspired Gaussian Splatting for HDR Novel View SynthesisHuimin Zeng, Yue Bai, hailing wang, Yun FuCVPR 2026 · 1 citation
- LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime PhotographyTingyu Yang, Yuan Cheng, Xiaoyun YuanSIGGRAPH 2026
Builds on27
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
- Zero-Shot Text-to-Image GenerationAditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray et al.ICML 2021 · 6,356 citations
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion ModelsAlexander Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam et al.ICML 2022 · 4,691 citations
- RePaint: Inpainting using Denoising Diffusion Probabilistic ModelsAndreas Lugmayr, Martin Danelljan, Andrés Romero, Fisher Yu et al.CVPR 2022 · 1,425 citations
Related papers
- GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the WildChao Wang, Ana Serrano, Xingang Pan, Bin Chen et al.ICCV 2023 · 29 citations
- SeHDR: Single-Exposure HDR Novel View Synthesis Via 3D Gaussian BracketingYiyu Li, Haoyuan Wang, Ke Xu, Gerhard Petrus Hancke et al.ICCV 2025 · 2 citations
- UltraFusion: Ultra High Dynamic Imaging using Exposure FusionZixuan Chen, Yujin Wang, Xin Cai, Zhiyuan You et al.CVPR 2025
- UltraLED: Learning to See Everything in Ultra-High Dynamic Range ScenesYuang Meng, Xin Jin, Lina Lei, Chun-Le Guo et al.NeurIPS 2025 · 8 citations
- Event-Guided HDR Reconstruction with Diffusion PriorsYixin Yang, Jiawei Zhang, Yang Zhang, Yunxuan Wei et al.ICCV 2025 · 4 citations
