Cargando…
Image Compression Based on Hybrid Domain Attention and Postprocessing Enhancement
Deep learning-based image compression methods have made significant achievements recently, of which the two key components are the entropy model for latent representations and the encoder-decoder network. Both the inaccurate estimation of the entropy estimation model and the existence of information...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947896/ https://www.ncbi.nlm.nih.gov/pubmed/35341171 http://dx.doi.org/10.1155/2022/4926124 |
_version_ | 1784674546087886848 |
---|---|
author | Bao, Yuting Tao, Yuwen Qian, Pengjiang |
author_facet | Bao, Yuting Tao, Yuwen Qian, Pengjiang |
author_sort | Bao, Yuting |
collection | PubMed |
description | Deep learning-based image compression methods have made significant achievements recently, of which the two key components are the entropy model for latent representations and the encoder-decoder network. Both the inaccurate estimation of the entropy estimation model and the existence of information redundancy in latent representations lead to a reduction in the compression efficiency. To address these issues, the study suggests an image compression method based on a hybrid domain attention mechanism and postprocessing improvement. This study embeds hybrid domain attention modules as nonlinear transformers in both the main encoder-decoder network and the hyperprior network, aiming at constructing more compact latent features and hyperpriors and then model the latent features as parametric Gaussian-scale mixture models to obtain more precise entropy estimation. In addition, we propose a solution to the errors introduced by quantization in image compression by adding an inverse quantization module. On the decoding side, we also provide a postprocessing enhancement module to further increase image compression performance. The experimental results show that the peak signal-to-noise rate (PSNR) and multiscale structural similarity (MS-SSIM) of the proposed method are higher than those of traditional compression methods and advanced neural network-based methods. |
format | Online Article Text |
id | pubmed-8947896 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Hindawi |
record_format | MEDLINE/PubMed |
spelling | pubmed-89478962022-03-25 Image Compression Based on Hybrid Domain Attention and Postprocessing Enhancement Bao, Yuting Tao, Yuwen Qian, Pengjiang Comput Intell Neurosci Research Article Deep learning-based image compression methods have made significant achievements recently, of which the two key components are the entropy model for latent representations and the encoder-decoder network. Both the inaccurate estimation of the entropy estimation model and the existence of information redundancy in latent representations lead to a reduction in the compression efficiency. To address these issues, the study suggests an image compression method based on a hybrid domain attention mechanism and postprocessing improvement. This study embeds hybrid domain attention modules as nonlinear transformers in both the main encoder-decoder network and the hyperprior network, aiming at constructing more compact latent features and hyperpriors and then model the latent features as parametric Gaussian-scale mixture models to obtain more precise entropy estimation. In addition, we propose a solution to the errors introduced by quantization in image compression by adding an inverse quantization module. On the decoding side, we also provide a postprocessing enhancement module to further increase image compression performance. The experimental results show that the peak signal-to-noise rate (PSNR) and multiscale structural similarity (MS-SSIM) of the proposed method are higher than those of traditional compression methods and advanced neural network-based methods. Hindawi 2022-03-17 /pmc/articles/PMC8947896/ /pubmed/35341171 http://dx.doi.org/10.1155/2022/4926124 Text en Copyright © 2022 Yuting Bao et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Article Bao, Yuting Tao, Yuwen Qian, Pengjiang Image Compression Based on Hybrid Domain Attention and Postprocessing Enhancement |
title | Image Compression Based on Hybrid Domain Attention and Postprocessing Enhancement |
title_full | Image Compression Based on Hybrid Domain Attention and Postprocessing Enhancement |
title_fullStr | Image Compression Based on Hybrid Domain Attention and Postprocessing Enhancement |
title_full_unstemmed | Image Compression Based on Hybrid Domain Attention and Postprocessing Enhancement |
title_short | Image Compression Based on Hybrid Domain Attention and Postprocessing Enhancement |
title_sort | image compression based on hybrid domain attention and postprocessing enhancement |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947896/ https://www.ncbi.nlm.nih.gov/pubmed/35341171 http://dx.doi.org/10.1155/2022/4926124 |
work_keys_str_mv | AT baoyuting imagecompressionbasedonhybriddomainattentionandpostprocessingenhancement AT taoyuwen imagecompressionbasedonhybriddomainattentionandpostprocessingenhancement AT qianpengjiang imagecompressionbasedonhybriddomainattentionandpostprocessingenhancement |