{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/frequency-aware-transformer-for-learned-image","title":"Frequency-Aware Transformer for Learned Image Compression","arxiv_id":"2310.16387","date":"2023-10-25","proceeding":null,"authors":["Han Li","Shaohui Li","Wenrui Dai","Chenglin Li","Junni Zou","Hongkai Xiong"],"abstract":"Learned image compression (LIC) has gained traction as an effective solution for image storage and transmission in recent years. However, existing LIC methods are redundant in latent representation due to limitations in capturing anisotropic frequency components and preserving directional details. To overcome these challenges, we propose a novel frequency-aware transformer (FAT) block that for the first time achieves multiscale directional ananlysis for LIC. The FAT block comprises frequency-decomposition window attention (FDWA) modules to capture multiscale and directional frequency components of natural images. Additionally, we introduce frequency-modulation feed-forward network (FMFFN) to adaptively modulate different frequency components, improving rate-distortion performance. Furthermore, we present a transformer-based channel-wise autoregressive (T-CA) model that effectively exploits channel dependencies. Experiments show that our method achieves state-of-the-art rate-distortion performance compared to existing LIC methods, and evidently outperforms latest standardized codec VTM-12.1 by 14.5%, 15.1%, 13.0% in BD-rate on the Kodak, Tecnick, and CLIC datasets.","url_abs":"https://arxiv.org/abs/2310.16387v4","url_pdf":"https://arxiv.org/pdf/2310.16387v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"frequency-aware-transformer-for-learned-image","repo_url":"https://github.com/qingshi9974/iclr2024-ftic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-compression","task_name":"Image Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.16387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16387"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qingshi9974/iclr2024-ftic","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"15c613ecceb6aa71","entry":"img2windows","repo":"qingshi9974/iclr2024-ftic","repo_kind":"official","path":"models/flic.py","file_url":"https://github.com/qingshi9974/iclr2024-ftic/blob/HEAD/models/flic.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"15c613ecceb6aa71"}},{"code_sha256_prefix":"cd3178f088f029d1","entry":"ste_round","repo":"qingshi9974/iclr2024-ftic","repo_kind":"official","path":"models/flic.py","file_url":"https://github.com/qingshi9974/iclr2024-ftic/blob/HEAD/models/flic.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd3178f088f029d1"}},{"code_sha256_prefix":"8cb23a62748d3b1c","entry":"windows2img","repo":"qingshi9974/iclr2024-ftic","repo_kind":"official","path":"models/flic.py","file_url":"https://github.com/qingshi9974/iclr2024-ftic/blob/HEAD/models/flic.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8cb23a62748d3b1c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}