Snapshot compressive imaging (SCI) aims to capture the high-dimensional (usually 3D) images using a 2D sensor (detector) in a single snapshot. Though enjoying the advantages of low-bandwidth, low-power and low-cost, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging. The bottleneck lies in the reconstruction algorithms; they are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the widely used PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload and prove the global convergence of PnP-GAP under the SCI hardware constraints. By employing deep denoising priors, we first time show that PnP can recover a UHD color video ($3840\times 1644\times 48$ with PNSR above 30dB) from a snapshot 2D measurement. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm.
@inproceedings{Yuan20PnPSCI,
author = {Yuan, Xin and Liu, Yang and Suo, Jinli and Dai, Qionghai},
title = {Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
doi = {10.1109/CVPR42600.2020.00152},
year = {2020},
month = {6},
pages = {1447 -- 1457},
arxiv = {2003.13654},
url = {https://doi.org/10.1109/CVPR42600.2020.00152},
publisher = {IEEE/CVF},
type = {Conference Proceedings}
}