将经典去噪算法BM3D改造为可训练神经网络，兼顾性能与可解释性。
Deep Unfolded BM3D: Unrolling Non-local Collaborative Filtering into a Trainable Neural Network
- 用可学习的U-Net替代固定参数的协同滤波模块
- 在低剂量CT数据上实现更高PSNR和SSIM，尤其在高噪声下优势明显
- 适合需要高性能且重视模型可解释性的医学图像去噪任务
块匹配与三维滤波（BM3D）利用非局部自相似性先验进行去噪，但依赖固定参数。深度模型如U-Net更灵活，但常缺乏可解释性且跨噪声条件泛化能力差。本文提出深度展开式BM3D（DU-BM3D），通过将BM3D展开为可训练架构，用可学习的U-Net去噪器替代其固定协同滤波模块，保留了BM3D的非局部结构先验并支持端到端优化。在低剂量CT（LDCT）去噪任务中评估，结果表明其在不同噪声水平下均优于经典BM3D和独立的U-Net，尤其在高噪声条件下取得更高PSNR与SSIM值。
原文摘要 · Abstract (English)
Block-Matching and 3D Filtering (BM3D) exploits non-local self-similarity priors for denoising but relies on fixed parameters. Deep models such as U-Net are more flexible but often lack interpretability and fail to generalize across noise regimes. In this study, we propose Deep Unfolded BM3D (DU-BM3D), a hybrid framework that unrolls BM3D into a trainable architecture by replacing its fixed collaborative filtering with a learnable U-Net denoiser. This preserves BM3D's non-local structural prior while enabling end-to-end optimization. We evaluate DU-BM3D on low-dose CT (LDCT) denoising and show that it outperforms classic BM3D and standalone U-Net across simulated LDCT at different noise levels, yielding higher PSNR and SSIM, especially in high-noise conditions.
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。