Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zeng, Fanhu, Tang, Hao, Shao, Yihua, Chen, Siyu, Shao, Ling, Wang, Yan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.12461
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916911623700480
author Zeng, Fanhu
Tang, Hao
Shao, Yihua
Chen, Siyu
Shao, Ling
Wang, Yan
author_facet Zeng, Fanhu
Tang, Hao
Shao, Yihua
Chen, Siyu
Shao, Ling
Wang, Yan
contents A high-performance image compression algorithm is crucial for real-time information transmission across numerous fields. Despite rapid progress in image compression, computational inefficiency and poor redundancy modeling still pose significant bottlenecks, limiting practical applications. Inspired by the effectiveness of state space models (SSMs) in capturing long-range dependencies, we leverage SSMs to address computational inefficiency in existing methods and improve image compression from multiple perspectives. In this paper, we integrate the advantages of SSMs for better efficiency-performance trade-off and propose an enhanced image compression approach through refined context modeling, which we term MambaIC. Specifically, we explore context modeling to adaptively refine the representation of hidden states. Additionally, we introduce window-based local attention into channel-spatial entropy modeling to reduce potential spatial redundancy during compression, thereby increasing efficiency. Comprehensive qualitative and quantitative results validate the effectiveness and efficiency of our approach, particularly for high-resolution image compression. Code is released at https://github.com/AuroraZengfh/MambaIC.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12461
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MambaIC: State Space Models for High-Performance Learned Image Compression
Zeng, Fanhu
Tang, Hao
Shao, Yihua
Chen, Siyu
Shao, Ling
Wang, Yan
Computer Vision and Pattern Recognition
Image and Video Processing
A high-performance image compression algorithm is crucial for real-time information transmission across numerous fields. Despite rapid progress in image compression, computational inefficiency and poor redundancy modeling still pose significant bottlenecks, limiting practical applications. Inspired by the effectiveness of state space models (SSMs) in capturing long-range dependencies, we leverage SSMs to address computational inefficiency in existing methods and improve image compression from multiple perspectives. In this paper, we integrate the advantages of SSMs for better efficiency-performance trade-off and propose an enhanced image compression approach through refined context modeling, which we term MambaIC. Specifically, we explore context modeling to adaptively refine the representation of hidden states. Additionally, we introduce window-based local attention into channel-spatial entropy modeling to reduce potential spatial redundancy during compression, thereby increasing efficiency. Comprehensive qualitative and quantitative results validate the effectiveness and efficiency of our approach, particularly for high-resolution image compression. Code is released at https://github.com/AuroraZengfh/MambaIC.
title MambaIC: State Space Models for High-Performance Learned Image Compression
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2503.12461