ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
arXiv:1706.07929
Abstract
With the aim of developing a fast yet accurate algorithm for compressive sensing (CS) reconstruction of natural images, we combine in this paper the merits of two existing categories of CS methods: the structure insights of traditional optimization-based methods and the speed of recent network-based ones. Specifically, we propose a novel structured deep network, dubbed ISTA-Net, which is inspired by the Iterative Shrinkage-Thresholding Algorithm (ISTA) for optimizing a general norm CS reconstruction model. To cast ISTA into deep network form, we develop an effective strategy to solve the proximal mapping associated with the sparsity-inducing regularizer using nonlinear transforms. All the parameters in ISTA-Net (\eg nonlinear transforms, shrinkage thresholds, step sizes, etc.) are learned end-to-end, rather than being hand-crafted. Moreover, considering that the residuals of natural images are more compressible, an enhanced version of ISTA-Net in the residual domain, dubbed {ISTA-Net}, is derived to further improve CS reconstruction. Extensive CS experiments demonstrate that the proposed ISTA-Nets outperform existing state-of-the-art optimization-based and network-based CS methods by large margins, while maintaining fast computational speed. Our source codes are available: \textsl{http://jianzhang.tech/projects/ISTA-Net}.
arXiv comment10 pages, 6 figures, 4 Tables. To appear in CVPR 2018
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- TensorFlow: A system for large-scale machine learning
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
- Compressed Sensing for Energy-Efficient Wireless Telemonitoring of Noninvasive Fetal ECG via Block Sparse Bayesian Learning
- Imaging With Nature: Compressive Imaging Using a Multiply Scattering Medium
- Image Compressive Sensing Recovery Using Adaptively Learned Sparsifying Basis via L0 Minimization
- Maximal Sparsity with Deep Networks?
- One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models
- A Deep Learning Approach to Block-based Compressed Sensing of Images