无需训练即可提升过曝区域的HDR重建质量
HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusion
- 用扩散模型修复过曝区域，结合文本引导与SDEdit优化
- 在标准数据集和真实场景中显著提升视觉质量和指标表现
- 适合希望不改架构就增强现有HDR方法的研究者
单张低动态范围（LDR）图像到高动态范围（HDR）重建在过曝区域仍具挑战性，传统方法因信息完全丢失而失效。本文提出一种无需训练的方法，通过基于扩散的修补技术增强现有的间接与直接HDR重建方法。该方法结合文本引导的扩散模型与SDEdit精炼机制，在过曝区域生成合理内容，同时保持多曝光LDR图像间的亮度一致性。相比需大量训练的以往方法，本方案通过迭代补偿机制无缝集成至现有HDR重建流程，确保多曝光间的一致性。在标准HDR数据集及真实场景图像上均取得显著的感知质量与量化指标提升，有效恢复复杂场景中的自然细节，同时保留原有方法的优势。项目主页：https://github.com/EusdenLin/HDR-Reconstruction-Boosting
原文摘要 · Abstract (English)
Single LDR to HDR reconstruction remains challenging for over-exposed regions where traditional methods often fail due to complete information loss. We present a training-free approach that enhances existing indirect and direct HDR reconstruction methods through diffusion-based inpainting. Our method combines text-guided diffusion models with SDEdit refinement to generate plausible content in over-exposed areas while maintaining consistency across multi-exposure LDR images. Unlike previous approaches requiring extensive training, our method seamlessly integrates with existing HDR reconstruction techniques through an iterative compensation mechanism that ensures luminance coherence across multiple exposures. We demonstrate significant improvements in both perceptual quality and quantitative metrics on standard HDR datasets and in-the-wild captures. Results show that our method effectively recovers natural details in challenging scenarios while preserving the advantages of existing HDR reconstruction pipelines. Project page: https://github.com/EusdenLin/HDR-Reconstruction-Boosting
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。