Currently, image-denoising methods based on deep learning cannot adequately reconcile contextual semantic information and spatial details. To take these information optimizations into consideration, in this paper, we propose a Context-Space Progressive Collaborative Network (CS-PCN) for image denoising. CS-PCN is a multi-stage hierarchical architecture composed of a context mining siamese sub-network (CM2S) and a space synthesis sub-network (3S). CM2S aims at extracting rich multi-scale contextual information by sequentially connecting multi-layer feature processors (MLFP) for semantic information pre-processing, attention encoder-decoders (AED) for multi-scale information, and multi-conv attention controllers (MCAC) for supervised feature fusion. 3S parallels MLFP and a single-scale cascading block to learn image details, which not only maintains the contextual information but also emphasizes the complementary spatial ones. Experimental results show that CS-PCN achieves significant performance improvement in synthetic and real-world noise removal.

翻译：当前，基于深度学习的图像去噪方法无法充分协调上下文语义信息与空间细节。为统筹优化这两类信息，本文提出一种上下文-空间渐进式协作网络（CS-PCN）用于图像去噪。CS-PCN采用多阶段分层架构，由上下文挖掘孪生子网络（CM2S）与空间合成子网络（3S）组成。CM2S通过依次连接多层特征处理器（MLFP）进行语义信息预处理、注意力编码器-解码器（AED）提取多尺度信息、以及多卷积注意力控制器（MCAC）实现监督特征融合，旨在提取丰富的多尺度上下文信息。3S并行使用MLFP与单尺度级联模块学习图像细节，既保持上下文信息又强调互补的空间信息。实验结果表明，CS-PCN在合成噪声与真实噪声去除任务中均取得了显著的性能提升。