Learned Image Compression with Dictionary-based Entropy Model

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lu, Jingbo, Zhang, Leheng, Zhou, Xingyu, Li, Mu, Li, Wen, Gu, Shuhang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910944603406336
author Lu, Jingbo
Zhang, Leheng
Zhou, Xingyu
Li, Mu
Li, Wen
Gu, Shuhang
author_facet Lu, Jingbo
Zhang, Leheng
Zhou, Xingyu
Li, Mu
Li, Wen
Gu, Shuhang
contents Learned image compression methods have attracted great research interest and exhibited superior rate-distortion performance to the best classical image compression standards of the present. The entropy model plays a key role in learned image compression, which estimates the probability distribution of the latent representation for further entropy coding. Most existing methods employed hyper-prior and auto-regressive architectures to form their entropy models. However, they only aimed to explore the internal dependencies of latent representation while neglecting the importance of extracting prior from training data. In this work, we propose a novel entropy model named Dictionary-based Cross Attention Entropy model, which introduces a learnable dictionary to summarize the typical structures occurring in the training dataset to enhance the entropy model. Extensive experimental results have demonstrated that the proposed model strikes a better balance between performance and latency, achieving state-of-the-art results on various benchmark datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00496
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learned Image Compression with Dictionary-based Entropy Model
Lu, Jingbo
Zhang, Leheng
Zhou, Xingyu
Li, Mu
Li, Wen
Gu, Shuhang
Computer Vision and Pattern Recognition
Learned image compression methods have attracted great research interest and exhibited superior rate-distortion performance to the best classical image compression standards of the present. The entropy model plays a key role in learned image compression, which estimates the probability distribution of the latent representation for further entropy coding. Most existing methods employed hyper-prior and auto-regressive architectures to form their entropy models. However, they only aimed to explore the internal dependencies of latent representation while neglecting the importance of extracting prior from training data. In this work, we propose a novel entropy model named Dictionary-based Cross Attention Entropy model, which introduces a learnable dictionary to summarize the typical structures occurring in the training dataset to enhance the entropy model. Extensive experimental results have demonstrated that the proposed model strikes a better balance between performance and latency, achieving state-of-the-art results on various benchmark datasets.
title Learned Image Compression with Dictionary-based Entropy Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.00496