Saved in:
Bibliographic Details
Main Authors: Fu, Nianxiang, Zhang, Junxi, Wang, Huairui, Chen, Zhenzhong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.13967
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913225482698752
author Fu, Nianxiang
Zhang, Junxi
Wang, Huairui
Chen, Zhenzhong
author_facet Fu, Nianxiang
Zhang, Junxi
Wang, Huairui
Chen, Zhenzhong
contents In this paper, we extend our prior research named DKIC and propose the perceptual-oriented learned image compression method, PO-DKIC. Specifically, DKIC adopts a dynamic kernel-based dynamic residual block group to enhance the transform coding and an asymmetric space-channel context entropy model to facilitate the estimation of gaussian parameters. Based on DKIC, PO-DKIC introduces PatchGAN and LPIPS loss to enhance visual quality. Furthermore, to maximize the overall perceptual quality under a rate constraint, we formulate this challenge into a constrained programming problem and use the Linear Integer Programming method for resolution. The experiments demonstrate that our proposed method can generate realistic images with richer textures and finer details when compared to state-of-the-art image compression techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13967
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Perceptual-oriented Learned Image Compression with Dynamic Kernel
Fu, Nianxiang
Zhang, Junxi
Wang, Huairui
Chen, Zhenzhong
Multimedia
In this paper, we extend our prior research named DKIC and propose the perceptual-oriented learned image compression method, PO-DKIC. Specifically, DKIC adopts a dynamic kernel-based dynamic residual block group to enhance the transform coding and an asymmetric space-channel context entropy model to facilitate the estimation of gaussian parameters. Based on DKIC, PO-DKIC introduces PatchGAN and LPIPS loss to enhance visual quality. Furthermore, to maximize the overall perceptual quality under a rate constraint, we formulate this challenge into a constrained programming problem and use the Linear Integer Programming method for resolution. The experiments demonstrate that our proposed method can generate realistic images with richer textures and finer details when compared to state-of-the-art image compression techniques.
title Perceptual-oriented Learned Image Compression with Dynamic Kernel
topic Multimedia
url https://arxiv.org/abs/2401.13967