Multi-Scale Deep Networks for Image Compressed Sensing
Authors:
- 1 October 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 46-50
Abstract
As a successful deep model applied in image compressed sensing, the Compressed Sensing Network (CSNet) has demonstrated superior performance to the previous handcrafted models in both running speed and reconstruction quality. However, CSNet trains different models for different sampling rates that hinders it from practical usage since too many models need to store. In this paper, we propose multi-scale deep network for image compressed sensing. We still use a sampling network to learn the sampling operator and implement the compressed sampling process. Given the compressed measurements, the reconstruction network directly maps them to the desired reconstructed images. There are three main differences in comparison with CSNet. Firstly, this paper proposes to use an unified deep reconstruction network for all sampling rates that decreases large amount of storage requirements. Secondly, we redesign a better deep reconstruction network using the popular residual learning technology. Finally, we investigate an image local smooth prior based loss function to enhance image structural information. Extensive experimental results show that the proposed multi-scale deep network based image compressed sensing method outperforms many other state-of-the-art methods.Keywords
This publication has 11 references indexed in Scilit:
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Single image super-resolution from transformed self-exemplars2015
- Block-Based Compressive Sensing Coding of Natural Images by Local Structural Measurement Matrix2015
- Group-Based Sparse Representation for Image RestorationIEEE Transactions on Image Processing, 2014
- Measurement coding for compressive imaging using a structural measuremnet matrix2013
- Compressed-sensing recovery of images and video using multihypothesis predictions2011
- Contour Detection and Hierarchical Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Block Compressed Sensing of Natural Images2007
- Compressed sensingIEEE Transactions on Information Theory, 2006
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002