Conditional Probability Models for Deep Image Compression

Mentzer, Fabian; Agustsson, Eirikur; Tschannen, Michael; Timofte, Radu; Gool, Luc Van

doi:10.1109/cvpr.2018.00462

Cited by 482 publications

(512 citation statements)

References 29 publications

Supporting

Mentioning

511

Contrasting

Order By: Relevance

“…For example, an uncompressed grayscale image has eight bpp. We first compare the proposed CCNs with mask convolutional networks (MCNs) [24], [25], PixelCNN++ [22], and side information networks (SINs) [19] for entropy modeling. As a special case of CCNs, MCNs specify the raster coding order without using any code dividing technique (see Fig.…”

Section: A Lossless Image Compressionmentioning

confidence: 99%

Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression

You

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

It has long been understood that precisely estimating the probabilistic structure of natural visual images is crucial for image compression. Despite remarkable success of recent end-toend optimized image compression, the latent code representation is assumed to be fully statistically factorized such that the entropy modeling is feasible. Here we describe context-based convolutional networks (CCNs) that exploit statistical redundancies in the codes for improved entropy modeling. We introduce a 3D zigzag coding order together with a 3D code dividing technique to define proper context and to achieve parallel entropy decoding, both of which boil down to place translation-invariant binary masks on convolution filters of CCNs. We demonstrate the power of CCNs for entropy modeling in both lossless and lossy image compression. For the former, we directly apply a CCN to binarized image planes for estimating the Bernoulli distribution of each code. For the latter, the categorical distribution of each code is represented by a discretized mixture of Gaussian distributions, whose parameters are estimated by three CCNs. We jointly optimize the CCN-based entropy model with analysis and synthesis transforms for rate-distortion performance. Experiments on two image datasets show that the proposed lossless and lossy image compression methods based on CCNs generally exhibit better compression performance than existing methods with a manageable computational complexity.

show abstract

Section: A Lossless Image Compressionmentioning

confidence: 99%

Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression

You

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Each residual block comprises two convolutional layers (normalized using the batch norm) and uses PRelu as the activation function. Inspired by [28], we also use an identical shortcut connecting the input and output of the residual blocks, which improves the performance as revealed by the experiments. Let H = f f−de ( M, Θ de ) denote the output of the joint decoder, parameterized by Θ de , and M denote the estimate of M provided by the entropy decoder.…”

Section: A Feature Encoder and Decodermentioning

confidence: 99%

Deep Convolutional Compression For Massive MIMO CSI Feedback

Yang

Mashhadi

Gündüz

2019

2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP)

View full text Add to dashboard Cite

Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to achieve spatial diversity and multiplexing gains. In a frequency division duplex (FDD) multiuser massive MIMO network, each user needs to compress and feedback its downlink CSI to the BS. The CSI overhead scales with the numbers of antennas, users and subcarriers, and becomes a major bottleneck for the overall spectral efficiency. In this paper, we propose a deep learning (DL)-based CSI compression scheme, called DeepCMC, composed of convolutional layers followed by quantization and entropy coding blocks. In comparison with previous deep learning DL-based CSI reduction structures, DeepCMC includes quantization and entropy coding blocks and minimizes a weighted rate-distortion cost which enables a trade-off between the CSI quality and its feedback overhead. Simulation results demonstrate that DeepCMC outperforms the state of the art CSI compression schemes in terms of the reconstruction quality of CSI for the same compression rate.We also propose a distributed version of DeepCMC for a multi-user MIMO scenario to encode and reconstruct the CSI from multiple users in a distributed manner. Distributed DeepCMC not only utilizes the inherent CSI structures of a single MIMO user for compression, but also benefits from the correlations among the channel matrices of nearby users to further improve the performance in comparison with DeepCMC.

show abstract

“…There has been a plethora of work on learned, singleimage, lossy image compression [44,45,4,5,43,31,35,33,24]. These works generally use nonlinear transforms through convolutional neural network (CNN) layers to encode an image into a latent space, which is then quantized into discrete symbols.…”

Section: A Review On Deep Image Compressionmentioning

confidence: 99%

DSIC: Deep Stereo Image Compression

Liu¹,

Wang

Urtasun³

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

In this paper we tackle the problem of stereo image compression, and leverage the fact that the two images have overlapping fields of view to further compress the representations. Our approach leverages state-of-the-art singleimage compression autoencoders and enhances the compression with novel parametric skip functions to feed fully differentiable, disparity-warped features at all levels to the encoder/decoder of the second image. Moreover, we model the probabilistic dependence between the image codes using a conditional entropy model. Our experiments show an impressive 30 -50% reduction in the second image bitrate at low bitrates compared to deep single-image compression, and a 10 -20% reduction at higher bitrates.

show abstract

Conditional Probability Models for Deep Image Compression

Cited by 482 publications

References 29 publications

Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression

Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression

Deep Convolutional Compression For Massive MIMO CSI Feedback

DSIC: Deep Stereo Image Compression

Contact Info

Product

Resources

About