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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper8
- GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDRChristophe Bolduc, Yannick Hold-Geoffroy, Jean-François LalondeICCV 2025 · 被引用 14 次
- HDR Image Generation via Gain Map Decomposed DiffusionYuanshen Guan, Ruikang Xu, Yinuo Liao, Mingde Yao 等ICCV 2025 · 被引用 1 次
- VENI: Variational Encoder for Natural IlluminationPaul Walker, James A. D. Gardner, Andreea Ardelean, William A. P. Smith 等CVPR 2026 · 被引用 1 次
- Physically Inspired Gaussian Splatting for HDR Novel View SynthesisHuimin Zeng, Yue Bai, hailing wang, Yun FuCVPR 2026 · 被引用 1 次
- LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime PhotographyTingyu Yang, Yuan Cheng, Xiaoyun YuanSIGGRAPH 2026
它引用的顶会 Paper27
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li 等NeurIPS 2022 · 被引用 8,965 次
- Zero-Shot Text-to-Image GenerationAditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray 等ICML 2021 · 被引用 6,356 次
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion ModelsAlexander Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam 等ICML 2022 · 被引用 4,691 次
- RePaint: Inpainting using Denoising Diffusion Probabilistic ModelsAndreas Lugmayr, Martin Danelljan, Andrés Romero, Fisher Yu 等CVPR 2022 · 被引用 1,425 次
相关 Paper
- GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the WildChao Wang, Ana Serrano, Xingang Pan, Bin Chen 等ICCV 2023 · 被引用 29 次
- SeHDR: Single-Exposure HDR Novel View Synthesis Via 3D Gaussian BracketingYiyu Li, Haoyuan Wang, Ke Xu, Gerhard Petrus Hancke 等ICCV 2025 · 被引用 2 次
- UltraFusion: Ultra High Dynamic Imaging using Exposure FusionZixuan Chen, Yujin Wang, Xin Cai, Zhiyuan You 等CVPR 2025
- UltraLED: Learning to See Everything in Ultra-High Dynamic Range ScenesYuang Meng, Xin Jin, Lina Lei, Chun-Le Guo 等NeurIPS 2025 · 被引用 8 次
- Event-Guided HDR Reconstruction with Diffusion PriorsYixin Yang, Jiawei Zhang, Yang Zhang, Yunxuan Wei 等ICCV 2025 · 被引用 4 次
