Deep Tensor ADMM-Net for Snapshot Compressive Imaging

Jiawei Ma, Xiao-Yang Liu, Zheng Shou, Xin Yuan; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 10223-10232


Snapshot compressive imaging (SCI) systems have been developed to capture high-dimensional (> 3) signals using low-dimensional off-the-shelf sensors, i.e., mapping multiple video frames into a single measurement frame. One key module of a SCI system is an accurate decoder that recovers the original video frames. However, existing model-based decoding algorithms require exhaustive parameter tuning with prior knowledge and cannot support practical applications due to the extremely long running time. In this paper, we propose a deep tensor ADMM-Net for video SCI systems that provides high-quality decoding in seconds. Firstly, we start with a standard tensor ADMM algorithm, unfold its inference iterations into a layer-wise structure, and design a deep neural network based on tensor operations. Secondly, instead of relying on a pre-specified sparse representation domain, the network learns the domain of low-rank tensor through stochastic gradient descent. It is worth noting that the proposed deep tensor ADMM-Net has potentially mathematical interpretations. On public video data, the simulation results show the proposed method achieves average 0.8 ~ 2.5 dB improvement in PSNR and 0.07 ~ 0.1 in SSIM, and 1500x~ 3600 xspeedups over the state-of-the-art methods. On real data captured by SCI cameras, the experimental results show comparable visual results with the state-of-the-art methods but in much shorter running time.

Related Material

[pdf] [supp]
author = {Ma, Jiawei and Liu, Xiao-Yang and Shou, Zheng and Yuan, Xin},
title = {Deep Tensor ADMM-Net for Snapshot Compressive Imaging},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}