Deep network-based image Compressed Sensing (CS) has attracted much attention in recent years. However, the existing deep network-based CS schemes either reconstruct the target image in a block-by-block manner that leads to serious block artifacts or train the deep network as a black box that brings about limited insights of image prior knowledge. In this paper, a novel image CS framework using non-local neural network (NL-CSNet) is proposed, which utilizes the non-local self-similarity priors with deep network to improve the reconstruction quality. In the proposed NL-CSNet, two non-local subnetworks are constructed for utilizing the non-local self-similarity priors in the measurement domain and the multi-scale feature domain respectively. Specifically, in the subnetwork of measurement domain, the long-distance dependencies between the measurements of different image blocks are established for better initial reconstruction. Analogically, in the subnetwork of multi-scale feature domain, the affinities between the dense feature representations are explored in the multi-scale space for deep reconstruction. Furthermore, a novel loss function is developed to enhance the coupling between the non-local representations, which also enables an end-to-end training of NL-CSNet. Extensive experiments manifest that NL-CSNet outperforms existing state-of-the-art CS methods, while maintaining fast computational speed.
翻译:近年来,基于网络的深层图像压缩(CS)已引起许多关注,但现有的基于网络的深层图像压缩(CS)方案要么以逐条方式重建目标图像,导致形成严重的块状文物,要么将深层网络训练成一个黑盒,对先前的图像了解有限。在本文中,提议采用非本地神经网络(NL-CSNet)的新图像 CS框架,利用非本地自我相似的前身和深层网络来提高重建质量。在拟议的NL-CSNet中,建立了两个非本地子网络,分别利用测量域域和多尺度域域的非本地自我相似的前身来重建目标图像。具体地说,在测量域子网子网络中,不同图像区块测量之间的长距离依赖性已经建立起来,以更好地进行初步重建。在多尺度特征域网子网子网子网下,为深层重建探索密集地貌图示之间的近似关系。此外,还开发了两个新的损失功能,以分别利用非本地的自我相似性前置前科,同时进行非本地的CS-LA型快速分析。