{"ID":2886794,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02192","arxiv_id":"2508.02192","title":"Content-Aware Mamba for Learned Image Compression","abstract":"Recent learned image compression (LIC) leverages Mamba-style state-space models (SSMs) for global receptive fields with linear complexity. However, the standard Mamba adopts content-agnostic, predefined raster (or multi-directional) scans under strict causality. This rigidity hinders its ability to effectively eliminate redundancy between tokens that are content-correlated but spatially distant. We introduce Content-Aware Mamba (CAM), an SSM that dynamically adapts its processing to the image content. Specifically, CAM overcomes prior limitations with two novel mechanisms. First, it replaces the rigid scan with a content-adaptive token permutation strategy to prioritize interactions between content-similar tokens regardless of their location. Second, it overcomes the sequential dependency by injecting sample-specific global priors into the state-space model, which effectively mitigates the strict causality without multi-directional scans. These innovations enable CAM to better capture global redundancy while preserving computational efficiency. Our Content-Aware Mamba-based LIC model (CMIC) achieves state-of-the-art rate-distortion performance, surpassing VTM-21.0 by 15.91%, 21.34%, and 17.58% in BD-rate on the Kodak, Tecnick, and CLIC datasets, respectively. Code will be released at https://github.com/UnoC-727/CMIC.","short_abstract":"Recent learned image compression (LIC) leverages Mamba-style state-space models (SSMs) for global receptive fields with linear complexity. However, the standard Mamba adopts content-agnostic, predefined raster (or multi-directional) scans under strict causality. This rigidity hinders its ability to effectively eliminat...","url_abs":"https://arxiv.org/abs/2508.02192","url_pdf":"https://arxiv.org/pdf/2508.02192v6","authors":"[\"Yunuo Chen\",\"Zezheng Lyu\",\"Bing He\",\"Hongwei Hu\",\"Qi Wang\",\"Yuan Tian\",\"Li Song\",\"Wenjun Zhang\",\"Guo Lu\"]","published":"2025-08-04T08:42:23Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":611350,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2886794,"paper_url":"https://arxiv.org/abs/2508.02192","paper_title":"Content-Aware Mamba for Learned Image Compression","repo_url":"https://github.com/UnoC-727/CMIC","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}