无需成对数据，用扩散模型单图去反光，效果优于当前最佳。
Single-image reflection removal via self-supervised diffusion models
- 结合循环一致性与扩散模型，分解图像成分
- 在三组数据集上均超越现有方法，尤其在博物馆场景表现突出
- 适合图像修复、逆向渲染等需要真实场景处理的研究者
透过透明表面拍摄的图像常因反光而质量下降，现有去反光方法受限于真实配对样本稀缺。本文提出一种混合方法，结合循环一致性与去噪扩散概率模型（DDPM），在无配对训练数据条件下有效去除单张图像中的反光。该方法包含反射去除网络（RRN），利用DDPM建模分解过程并恢复透射图像；以及反射合成网络（RSN），通过非线性注意力机制将分离成分重新合成输入图像。实验在SIR²、基于闪光灯的反光去除（FRR）数据集及新提出的博物馆反光去除（MRR）数据集上验证了有效性，性能优于当前最优方法。
原文摘要 · Abstract (English)
Reflections often degrade the visual quality of images captured through transparent surfaces, and reflection removal methods suffers from the shortage of paired real-world samples.This paper proposes a hybrid approach that combines cycle-consistency with denoising diffusion probabilistic models (DDPM) to effectively remove reflections from single images without requiring paired training data. The method introduces a Reflective Removal Network (RRN) that leverages DDPMs to model the decomposition process and recover the transmission image, and a Reflective Synthesis Network (RSN) that re-synthesizes the input image using the separated components through a nonlinear attention-based mechanism. Experimental results demonstrate the effectiveness of the proposed method on the SIR$^2$, Flash-Based Reflection Removal (FRR) Dataset, and a newly introduced Museum Reflection Removal (MRR) dataset, showing superior performance compared to state-of-the-art methods.
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。