用内部图像先验引导扩散模型去雾，减少幻觉、保持原图颜色
ProDehaze: Prompting Diffusion Models Toward Faithful Image Dehazing
- 引入结构提示与雾霾自校正机制，聚焦关键区域
- 在真实数据集上显著降低颜色偏移，提升去雾保真度
- 适合需要高保真度的图像去雾应用，如遥感或医学成像
近期基于大规模预训练扩散模型的去雾方法虽提升了视觉质量，但常出现幻觉，导致去雾结果与原图不符。为此，我们提出ProDehaze框架，利用内部图像先验引导预训练模型中的外部先验。引入两类选择性内部先验：在潜在空间中强调结构丰富区域的结构提示修复器，以及在解码过程中对齐清晰区域与输出分布的雾霾感知自校正精修器。在真实世界数据集上的大量实验表明，ProDehaze在图像去雾中实现了高保真效果，尤其有效减少颜色偏移。代码已开源：https://github.com/TianwenZhou/ProDehaze。
原文摘要 · Abstract (English)
Recent approaches using large-scale pretrained diffusion models for image dehazing improve perceptual quality but often suffer from hallucination issues, producing unfaithful dehazed image to the original one. To mitigate this, we propose ProDehaze, a framework that employs internal image priors to direct external priors encoded in pretrained models. We introduce two types of \textit{selective} internal priors that prompt the model to concentrate on critical image areas: a Structure-Prompted Restorer in the latent space that emphasizes structure-rich regions, and a Haze-Aware Self-Correcting Refiner in the decoding process to align distributions between clearer input regions and the output. Extensive experiments on real-world datasets demonstrate that ProDehaze achieves high-fidelity results in image dehazing, particularly in reducing color shifts. Our code is at https://github.com/TianwenZhou/ProDehaze.
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。