Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging

Abstract

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 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. The code is available at https://github.com/liuyang12/PnP-SCI.

CVPR 2020. Corrected a proof of convergence in previous version

References in corpus (11)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Rank Minimization for Snapshot Compressive Imaging
• Coded aperture compressive temporal imaging
• Compressive Hyperspectral Imaging with Side Information
• Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
• Adaptive Temporal Compressive Sensing for Video
• Classification and Reconstruction of High-Dimensional Signals from Low-Dimensional Features in the Presence of Side Information
• ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements
• Compressive Sensing via Low-Rank Gaussian Mixture Models
• Tree-Structure Bayesian Compressive Sensing for Video

Cited by in corpus (1)

• GAP-net for Snapshot Compressive Imaging