用状态空间模型提升图像压缩效率与质量，尤其适合高分辨率图像。
MambaIC: State Space Models for High-Performance Learned Image Compression
- 引入状态空间模型优化上下文建模，动态调整隐状态表示。
- 结合窗口注意力减少空间冗余，压缩速度更快、效果更优。
- 特别适合对高分辨率图像进行高效压缩，代码已开源。
高效图像压缩算法对众多领域的实时信息传输至关重要。尽管图像压缩技术发展迅速，但计算效率低下和冗余建模能力不足仍是主要瓶颈，制约了实际应用。受状态空间模型（SSMs）在捕捉长程依赖方面的启发，本文利用SSMs解决现有方法的计算效率问题，并从多角度提升图像压缩性能。提出一种改进的压缩方法MambaIC，通过精细化上下文建模，自适应优化隐藏状态表示；同时在通道-空间熵建模中引入窗口局部注意力，有效降低压缩过程中的潜在空间冗余，提升效率。定性与定量实验表明，该方法在高分辨率图像压缩上表现优异。代码已发布于 https://github.com/AuroraZengfh/MambaIC。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。