让普通图像生成模型也能输出逼真的高动态范围图像。
LEDiff: Latent Exposure Diffusion for HDR Generation
- 在潜在空间融合曝光信息，模仿人眼感知重建高动态范围。
- 仅用少量HDR数据即可提升模型对过曝与暗部细节的恢复能力。
- 适合需要真实光影效果的生成、渲染与摄影模拟场景。
尽管消费级显示设备已支持超过10档动态范围，但多数图像资产（如网络照片和生成式AI内容）仍受限于8位低动态范围（LDR），制约其在高动态范围（HDR）应用中的使用。当前尚无通用生成模型可产生物理上合理的高比特高动态范围内容。现有LDR转HDR方法常无法还原真实细节与物理合理的动态范围，尤其在剪切区域表现不佳。本文提出LEDiff，一种基于图像空间曝光融合思想的潜在空间融合方法，使预训练扩散模型具备生成HDR内容的能力。该方法仅需少量HDR数据即可让模型恢复过曝与暗部细节，实现从任意LDR图像到高质量HDR的转换。LEDiff不仅拓展了现有生成模型的动态范围能力，还可用于图像生成、基于图像的光照（生成HDR环境贴图）、景深模拟等需要线性HDR数据的场景，显著提升真实感质量。
原文摘要 · Abstract (English)
While consumer displays increasingly support more than 10 stops of dynamic range, most image assets such as internet photographs and generative AI content remain limited to 8-bit low dynamic range (LDR), constraining their utility across high dynamic range (HDR) applications. Currently, no generative model can produce high-bit, high-dynamic range content in a generalizable way. Existing LDR-to-HDR conversion methods often struggle to produce photorealistic details and physically-plausible dynamic range in the clipped areas. We introduce LEDiff, a method that enables a generative model with HDR content generation through latent space fusion inspired by image-space exposure fusion techniques. It also functions as an LDR-to-HDR converter, expanding the dynamic range of existing low-dynamic range images. Our approach uses a small HDR dataset to enable a pretrained diffusion model to recover detail and dynamic range in clipped highlights and shadows. LEDiff brings HDR capabilities to existing generative models and converts any LDR image to HDR, creating photorealistic HDR outputs for image generation, image-based lighting (HDR environment map generation), and photographic effects such as depth of field simulation, where linear HDR data is essential for realistic quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。