用扩散模型+小波抑制，提升复杂场景下图像分离的清晰度与细节保留。
The Diffusion Duet: Harmonizing Dual Channels with Wavelet Suppression for Image Separation
- 引入扩散模型与双通道架构，结合小波抑制模块实现双向去噪与特征解耦。
- 在雨雪去除任务中，PSNR达35.0023 dB（雨）和29.8108 dB（雪），优于现有方法。
- 特别适合处理强噪声、非线性混合下的图像复原与多源分离任务。
盲图像分离（BIS）是在未知混合方式且无源图像先验的情况下，从单一观测图像中同时估计并恢复多个独立源图像的逆问题。传统依赖统计独立性或CNN/GAN的方法难以刻画真实场景中的复杂特征分布，导致估计偏差、纹理失真及残留伪影。本文创新性地将扩散模型引入双通道BIS，提出高效双通道扩散分离模型（DCDSM）。该模型利用扩散模型的强大生成能力学习源图像特征分布并有效重建结构。设计新颖的小波抑制模块（WSM），嵌入双分支反向去噪过程，形成交互式分离网络，通过挖掘源图像间相互耦合的噪声特性增强细节分离能力。在含雨/雪及复杂混合的合成数据集上大量实验表明，DCDSM达到当前最优性能：1）图像恢复任务中，雨与雪去除的PSNR/SSIM分别为35.0023 dB/0.9549 和 29.8108 dB/0.9243，平均优于Histoformer和LDRCNet 1.2570 dB（PSNR）与0.0262/0.0289（SSIM）；2）复杂混合分离任务中，双源图像平均PSNR与SSIM达25.0049 dB与0.7997，分别领先对比方法4.1249 dB与0.0926。主观与客观评估均证实其在去除雨雪残留与保持细节方面的优势。
原文摘要 · Abstract (English)
Blind image separation (BIS) refers to the inverse problem of simultaneously estimating and restoring multiple independent source images from a single observation image under conditions of unknown mixing mode and without prior knowledge of the source images. Traditional methods relying on statistical independence assumptions or CNN/GAN variants struggle to characterize complex feature distributions in real scenes, leading to estimation bias, texture distortion, and artifact residue under strong noise and nonlinear mixing. This paper innovatively introduces diffusion models into dual-channel BIS, proposing an efficient Dual-Channel Diffusion Separation Model (DCDSM). DCDSM leverages diffusion models' powerful generative capability to learn source image feature distributions and reconstruct feature structures effectively. A novel Wavelet Suppression Module (WSM) is designed within the dual-branch reverse denoising process, forming an interactive separation network that enhances detail separation by exploiting the mutual coupling noise characteristic between source images. Extensive experiments on synthetic datasets containing rain/snow and complex mixtures demonstrate that DCDSM achieves state-of-the-art performance: 1) In image restoration tasks, it obtains PSNR/SSIM values of 35.0023 dB/0.9549 and 29.8108 dB/0.9243 for rain and snow removal respectively, outperforming Histoformer and LDRCNet by 1.2570 dB/0.9272 dB (PSNR) and 0.0262/0.0289 (SSIM) on average; 2) For complex mixture separation, the restored dual-source images achieve average PSNR and SSIM of 25.0049 dB and 0.7997, surpassing comparative methods by 4.1249 dB and 0.0926. Both subjective and objective evaluations confirm DCDSM's superiority in addressing rain/snow residue removal and detail preservation challenges.
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。