Image Compression Based on Compressive Sensing: End-to-End Comparison With JPEG

  title={Image Compression Based on Compressive Sensing: End-to-End Comparison With JPEG},
  author={Xin Yuan and Raziel Haimi-Cohen},
  journal={IEEE Transactions on Multimedia},
We present an end-to-end image compression system based on compressive sensing. [...] Key Method We study the parameters that influence the system performance, including (i) the choice of sensing matrix, (ii) the trade-off between quantization and compression ratio, and (iii) the reconstruction algorithms. We propose an effective method to jointly control the quantization step and compression ratio in order to achieve near optimal quality at any given bit rate. Furthermore, our proposed image compression system…Expand
Efficient Compressed Sensing Based Image Coding by Using Gray Transformation
This work uses a gray transformation to preprocess the original image firstly and then use CS to sample the transformed image, which can considerably improve the compression performance of CS-based image coding. Expand
Intra Prediction-Based Measurement Coding Algorithm for Block-Based Compressive Sensing Images
This work introduces intra prediction based measurement coding algorithm for giving an extra compression performance to measurement and uses structural sensing matrix made of sequency-ordered Walsh-Hadamard to achieve higher throughput than software. Expand
Comparison of Image Reconstruction Algorithms using Compressive Sensing
This paper is making a comparison between the performances of Orthogonal Matching Pursuit (OMP) and Regularised orthogonal matching Pursuits (ROMP) algorithms for image reconstruction. Expand
Comparison between CS and JPEG in terms of image compression
It is shown that images, recovered by using the Compressive Sensing approach, have higher PSNR values compared to the images under JPEG compression. Expand
Adaptive Compressive Imaging using Non-Random Dictionaries
Practical, real-time compressive sensing (CS) of images requires that an image is first partitioned into blocks to reduce the sensing matrix size. However, the blocks are found to have differingExpand
CSMCNet: Scalable Video Compressive Sensing Reconstruction with Interpretable Motion Estimation
  • Bowen Huang, Xiao Yan, Jinjia Zhou, Yibo Fan
  • Engineering
  • 2021
Most deep network methods for compressive sensing reconstruction suffer from the black-box characteristic of DNN. In this paper, a deep neural network with interpretable motion estimation namedExpand
Adaptive block compressed sensing - a technological analysis and survey on challenges, innovation directions and applications
This review paper studies the advantages, challenges and applications of applying ABCS for image compression, a variant of compressed sensing that exploits the sparsity of the signal for sampling the data. Expand
Drcas: Deep Restoration Network For Hardware Based Compressive Acquisition Scheme
A novel image acquisition scheme HCAS is proposed using hardware-based binning, bit truncation and JPEG compression, and a deep learning based reconstruction network DRCAS (Deep Restoration network for hardware based Compressed Acquisition Scheme) is developed for images acquired using HCAS. Expand
Effective Snapshot Compressive-spectral Imaging via Deep Denoising and Total Variation Priors
Snapshot compressive imaging (SCI) is a new type of compressive imaging system that compresses multiple frames of images into a single snapshot measurement, which enjoys low cost, low bandwidth, andExpand
Compressive Sampling Using a Pushframe Camera
The recently described pushframe imager, a parallelized single pixel camera capturing with a pushbroom-like motion, is intrinsically suited to both remote-sensing and compressive sampling. ItExpand


Joint Sampling Rate and Bit-Depth Optimization in Compressive Video Sampling
This paper presents an adaptive and unidirectional CVS framework with rate-distortion (RD) optimized rate allocation, wherein it is proposed to implement “optimized” video sampling and measurement quantization with the estimated SR and B, respectively. Expand
An Efficient Deep Quantized Compressed Sensing Coding Framework of Natural Images
A novel deep network based CS coding framework of natural images that consists of three sub-networks that responsible for sampling, quantization and reconstruction, respectively that can be trained in the form of an end-to-end metric with a proposed rate-distortion optimization loss function. Expand
Efficient and Robust Image Coding and Transmission Based on Scrambled Block Compressive Sensing
The experimental results show that the proposed scheme can achieve higher R-D performance compared with the benchmark CS-based image coding and transmission schemes and achieves state-of-the-art coding efficiency with lower computational complexity at the encoder while still supporting error resilience. Expand
Robust Image Coding Based Upon Compressive Sensing
The compressive sensing (CS) principles are studied and an alternative coding paradigm with a number of descriptions is proposed based upon CS for high packet loss transmission and Experimental results show that the proposed CS-based codec is much more robust against lossy channels, while achieving higher rate-distortion performance. Expand
Snapshot Compressed Sensing: Performance Bounds and Algorithms
  • S. Jalali, Xin Yuan
  • Computer Science, Mathematics
  • IEEE Transactions on Information Theory
  • 2019
It is shown that, in the cases of both noise-free and noisy measurements, combining the proposed algorithms with a customized video compression code, designed to exploit nonlocal structures of video frames, significantly improves the state-of-the-art performance. Expand
Distributed Compressive Sensing for Cloud-Based Wireless Image Transmission
A new distributed compressive sensing (CS) scheme that can leverage similar images in the cloud and outperforms existing schemes both subjectively and objectively by up to 11 dB gains compared with the state-of-the-art transmission scheme with GD. Expand
Lensless Compressive Imaging
An anytime algorithm is proposed to reconstruct images from the compressive measurements; the algorithm produces a sequence of solutions that monotonically converge to the true signal (thus, anytime) and state-of-the-art results have been obtained. Expand
Deep networks for compressed image sensing
A deep network is proposed to recover the image, which imitates traditional compressed sensing reconstruction processes, and offers a very significant quality improvement compared against state-of-the-art ones. Expand
Regime Change: Bit-Depth Versus Measurement-Rate in Compressive Sensing
It is shown that there exist two distinct regimes of operation that correspond to high/low signal-to-noise ratio (SNR), and that in many practical applications it is better to operate in the quantization compression (QC) regime, even acquiring as few as 1 bit per measurement. Expand
Quantization effects on Compressed Sensing Video
It is shown that Gaussian quantization of the CVS coefficients produce higher quality reconstructed videos compared to using MPEG and uniform quantization, and the quantization matrix is robust against variations in the mean and standard deviations of the CS measurements among frames. Expand