In this paper, a deep neural network with interpretable motion compensation called CS-MCNet is proposed to realize high-quality and real-time decoding of video compressive sensing. Firstly, explicit multi-hypothesis motion compensation is applied in our network to extract correlation information of adjacent frames(as shown in Fig. 1), which improves the recover performance. And then, a residual module further narrows down the gap between reconstruction result and original signal. The overall architecture is interpretable by using algorithm unrolling, which brings the benefits of being able to transfer prior knowledge about the conventional algorithms. As a result, a PSNR of 22dB can be achieved at 64x compression ratio, which is about 4% to 9% better than state-of-the-art methods. In addition, due to the feed-forward architecture, the reconstruction can be processed by our network in real time and up to three orders of magnitude faster than traditional iterative methods.
@article{arxiv.2010.03780,
title = {CS-MCNet:A Video Compressive Sensing Reconstruction Network with Interpretable Motion Compensation},
author = {Bowen Huang and Jinjia Zhou and Xiao Yan and Ming'e Jing and Rentao Wan and Yibo Fan},
journal= {arXiv preprint arXiv:2010.03780},
year = {2020}
}