GAP-net for Snapshot Compressive Imaging

Abstract

Snapshot compressive imaging (SCI) systems aim to capture high-dimensional ($\ge 3$D) images in a single shot using 2D detectors. SCI devices include two main parts: a hardware encoder and a software decoder. The hardware encoder typically consists of an (optical) imaging system designed to capture {compressed measurements}. The software decoder on the other hand refers to a reconstruction algorithm that retrieves the desired high-dimensional signal from those measurements. In this paper, using deep unfolding ideas, we propose an SCI recovery algorithm, namely GAP-net, which unfolds the generalized alternating projection (GAP) algorithm. At each stage, GAP-net passes its current estimate of the desired signal through a trained convolutional neural network (CNN). The CNN operates as a denoiser that projects the estimate back to the desired signal space. For the GAP-net that employs trained auto-encoder-based denoisers, we prove a probabilistic global convergence result. Finally, we investigate the performance of GAP-net in solving video SCI and spectral SCI problems. In both cases, GAP-net demonstrates competitive performance on both synthetic and real data. In addition to having high accuracy and high speed, we show that GAP-net is flexible with respect to signal modulation implying that a trained GAP-net decoder can be applied in different systems. Our code is at https://github.com/mengziyi64/ADMM-net.

30 pages, 14 figures; State-of-the-art algorithms for Snapshot Compressive Imaging

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• 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
• Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
• Compressive Hyperspectral Imaging with Side Information
• Learned D-AMP: Principled Neural Network based Compressive Image Recovery
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
• ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements
• Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging

Cited by in corpus (7)

• RDFNet: Regional Dynamic FISTA-Net for Spectral Snapshot Compressive Imaging
• Memory-Efficient Network for Large-scale Video Compressive Sensing
• Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging
• Iterative Low-rank Network for Hyperspectral Image Denoising
• Theoretical Analysis of Binary Masks in Snapshot Compressive Imaging Systems
• MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing
• Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Network