ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements

Abstract

The goal of this paper is to present a non-iterative and more importantly an extremely fast algorithm to reconstruct images from compressively sensed (CS) random measurements. To this end, we propose a novel convolutional neural network (CNN) architecture which takes in CS measurements of an image as input and outputs an intermediate reconstruction. We call this network, ReconNet. The intermediate reconstruction is fed into an off-the-shelf denoiser to obtain the final reconstructed image. On a standard dataset of images we show significant improvements in reconstruction results (both in terms of PSNR and time complexity) over state-of-the-art iterative CS reconstruction algorithms at various measurement rates. Further, through qualitative experiments on real data collected using our block single pixel camera (SPC), we show that our network is highly robust to sensor noise and can recover visually better quality images than competitive algorithms at extremely low sensing rates of 0.1 and 0.04. To demonstrate that our algorithm can recover semantically informative images even at a low measurement rate of 0.01, we present a very robust proof of concept real-time visual tracking application.

Accepted at IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016

References in corpus (6)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Compressive Imaging via Approximate Message Passing with Image Denoising
• Designing Deep Networks for Surface Normal Estimation
• Dense Optical Flow Prediction from a Static Image
• Improved Total Variation based Image Compressive Sensing Recovery by Nonlocal Regularization

Cited by in corpus (13)

• AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
• DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing
• GAP-net for Snapshot Compressive Imaging
• Deep Learning-Guided Image Reconstruction from Incomplete Data
• Convolutional neural networks that teach microscopes how to image
• Learning to Invert: Signal Recovery via Deep Convolutional Networks
• ConvCSNet: A Convolutional Compressive Sensing Framework Based on Deep Learning
• Inferring Sparsity: Compressed Sensing using Generalized Restricted Boltzmann Machines
• Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging
• Deep Compressive Macroscopic Fluorescence Lifetime Imaging
• AMPA-Net: Optimization-Inspired Attention Neural Network for Deep Compressed Sensing
• Block Compressive Sensing of Image and Video with Nonlocal Lagrangian Multiplier and Patch-based Sparse Representation
• Deep neural network based sparse measurement matrix for image compressed sensing