用先验调制扩散模型，精准去除复杂场景的单图反射。
FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal
- 通过强度与高频先验实现空间自适应条件调节
- 分阶段训练，先粗后细提升结构保真度
- 适合处理真实场景中强反射与细节纠缠问题
单图反射去除（SIRR）在真实场景中极具挑战性，因反射强度空间变化大且与透射结构紧密耦合。本文提出基于先验调制的扩散模型（FUMO），引入显式先验以实现空间自适应条件调节和结构忠实恢复。从混合图像中直接提取两个先验：强度先验用于估计空间反射严重程度，高频先验通过多尺度残差聚合捕捉对细节敏感的响应。采用粗到精训练范式：第一阶段结合这些线索门控条件残差注入，聚焦于反射主导且结构敏感区域；第二阶段通过精细修正网络校正局部错位并锐化图像细节。在标准基准与野外复杂图像上的实验表明，该方法在定量指标上表现优异，且感知质量持续提升。代码已开源：https://github.com/Lucious-Desmon/FUMO。
原文摘要 · Abstract (English)
Single image reflection removal (SIRR) is challenging in real scenes, where reflection strength varies spatially and reflection patterns are tightly entangled with transmission structures. This paper presents a diffusion model with prior modulation framework (FUMO) that introduces explicit priors for spatially adaptive conditioning and structurally faithful restoration. Two priors are extracted directly from the mixed image, an intensity prior that estimates spatial reflection severity and a high-frequency prior that captures detail-sensitive responses via multi-scale residual aggregation. We propose a coarse-to-fine training paradigm. In the first stage, these cues are combined to gate the conditional residual injections, focusing the conditioning on regions that are both reflection-dominant and structure-sensitive. In the second stage, a fine-grained refinement network corrects local misalignment and sharpens fine details in the image space. Experiments conducted on both standard benchmarks and challenging images in the wild demonstrate competitive quantitative results and consistently improved perceptual quality. The code is released at https://github.com/Lucious-Desmon/FUMO.
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。