End-to-end learned image compression with conditional latent space modeling for entropy coding

Date

2021-01-24

Author

Yesilyurt, Aziz Berkay
Kamışlı, Fatih

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

199
views

0
downloads

The use of neural networks in image compression enables transforms and probability models for entropy coding which can process images based on much more complex models than the simple Gauss-Markov models in traditional compression methods. All at the expense of higher computational complexity. In the neural-network based image compression literature, various methods to model the dependencies in the transform domain/latent space are proposed. This work uses an alternative method to exploit the dependencies of the latent representation. The joint density of the latent representation is modeled as a product of conditional densities, which are learned using neural networks. However, each latent variable is not conditioned on all previous latent variables as in the chain rule of factoring joint distributions, but only on a few previous variables, in particular the left, upper and upper-left spatial neighbor variables based on a Markov property assumption for a simpler model and algorthm. The compression performance is comparable with the state- of-the-art compression models, while the conditional densities require a much simpler network and training time due to their simplicity and less number of parameters then its counterparts.

Subject Keywords

image compression, transform coding, deep learning, conditional modeling

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85099287734&origin=inward
https://hdl.handle.net/11511/90858

DOI

https://doi.org/10.23919/eusipco47968.2020.9287779

Conference Name

28th European Signal Processing Conference, EUSIPCO 2020

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

End-to-end learned image compression with conditional latent space modelling for entropy coding Yeşilyurt, Aziz Berkay; Kamışlı, Fatih; Department of Electrical and Electronics Engineering (2019) This thesis presents a lossy image compression system based on an end-to-end trainable neural network. Traditional compression algorithms use linear transformation, quantization and entropy coding steps that are designed based on simple models of the data and are aimed to be low complexity. In neural network based image compression methods, the processing steps, such as transformation and entropy coding, are performed using neural networks. The use of neural networks enables transforms or probability models...
Deep Learning-Based Hybrid Approach for Phase Retrieval IŞIL, ÇAĞATAY; Öktem, Sevinç Figen; KOÇ, AYKUT (2019-06-24) We develop a phase retrieval algorithm that utilizes the hybrid-input-output (HIO) algorithm with a deep neural network (DNN). The DNN architecture, which is trained to remove the artifacts of HIO, is used iteratively with HIO to improve the reconstructions. The results demonstrate the effectiveness of the approach with little additional cost.
DEEP LEARNING-BASED UNROLLED RECONSTRUCTION METHODS FOR COMPUTATIONAL IMAGING Bezek, Can Deniz; Öktem, Sevinç Figen; Department of Electrical and Electronics Engineering (2021-9-08) Computational imaging is the process of forming images from indirect measurements using computation. In this thesis, we develop deep learning-based unrolled reconstruction methods for various computational imaging modalities. Firstly, we develop two deep learning-based reconstruction methods for diffractive multi-spectral imaging. The first approach is based on plug-and-play regularization with deep denoisers whereas the second one is an end-to-end learned reconstruction based on unrolling. Secondly, we con...
Efficient algorithms for convolutional inverse problems in multidimensional imaging Doğan, Didem; Öktem, Figen S.; Department of Electrical and Electronics Engineering (2020) Computational imaging is the process of indirectly forming images from measurements using image reconstruction algorithms that solve inverse problems. In many inverse problems in multidimensional imaging such as spectral and depth imaging, the measurements are in the form of superimposed convolutions related to the unknown image. In this thesis, we first provide a general formulation for these problems named as convolutional inverse problems, and then develop fast and efficient image reconstruction algorith...
Fast Algorithms for Digital Computation of Linear Canonical Transforms Koc, Aykut; Öktem, Sevinç Figen; Ozaktas, Haldun M.; Kutay, M. Alper (2016-01-01) Fast and accurate algorithms for digital computation of linear canonical transforms (LCTs) are discussed. Direct numerical integration takes O.N-2/time, where N is the number of samples. Designing fast and accurate algorithms that take O. N logN/time is of importance for practical utilization of LCTs. There are several approaches to designing fast algorithms. One approach is to decompose an arbitrary LCT into blocks, all of which have fast implementations, thus obtaining an overall fast algorithm. Another a...

Citation Formats

A. B. Yesilyurt and F. Kamışlı, “End-to-end learned image compression with conditional latent space modeling for entropy coding,” presented at the 28th European Signal Processing Conference, EUSIPCO 2020, Amsterdam, Hollanda, 2021, Accessed: 00, 2021. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85099287734&origin=inward.