{"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/mlic-linear-complexity-multi-reference","title":"MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression","arxiv_id":"2307.15421","date":"2023-07-28","proceeding":null,"authors":["Wei Jiang","Jiayu Yang","Yongqi Zhai","Feng Gao","Ronggang Wang"],"abstract":"Recently, learned image compression has achieved impressive performance. The entropy model, which estimates the distribution of the latent representation, plays a crucial role in enhancing rate-distortion performance. However, existing global context modules rely on computationally intensive quadratic complexity computations to capture global correlations. This quadratic complexity imposes limitations on the potential of high-resolution image coding. Moreover, effectively capturing local, global, and channel-wise contexts with acceptable even linear complexity within a single entropy model remains a challenge. To address these limitations, we propose the Linear Complexity Multi-Reference Entropy Model (MEM++). MEM++ effectively captures the diverse range of correlations inherent in the latent representation. Specifically, the latent representation is first divided into multiple slices. When compressing a particular slice, the previously compressed slices serve as its channel-wise contexts. To capture local contexts without sacrificing performance, we introduce a novel checkerboard attention module. Additionally, to capture global contexts, we propose the linear complexity attention-based global correlations capturing by leveraging the decomposition of the softmax operation. The attention map of the previously decoded slice is implicitly computed and employed to predict global correlations in the current slice. Based on MEM++, we propose image compression model MLIC++. Extensive experimental evaluations demonstrate that our MLIC++ achieves state-of-the-art performance, reducing BD-rate by 13.39% on the Kodak dataset compared to VTM-17.0 in PSNR. Furthermore, MLIC++ exhibits linear GPU memory consumption with resolution, making it highly suitable for high-resolution image coding. Code and pre-trained models are available at https://github.com/JiangWeibeta/MLIC.","url_abs":"https://arxiv.org/abs/2307.15421v9","url_pdf":"https://arxiv.org/pdf/2307.15421v9.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":"mlic-linear-complexity-multi-reference","repo_url":"https://github.com/jiangweibeta/mlic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-compression","task_name":"Image Compression"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-compression-on-kodak","task":"Image Compression","dataset":"kodak","model":"MLIC++","rank_in_archive_order":2,"of":8,"metrics":{"BD-Rate over VTM-17.0":"-13.39"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.15421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15421"}},"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/jiangweibeta/mlic","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"f2cea3e9848ae52d","entry":"conv","repo":"jiangweibeta/mlic","repo_kind":"official","path":"MLIC++/modules/layers/conv.py","file_url":"https://github.com/jiangweibeta/mlic/blob/HEAD/MLIC%2B%2B/modules/layers/conv.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f2cea3e9848ae52d"}},{"code_sha256_prefix":"1afd37c576493fea","entry":"deconv","repo":"jiangweibeta/mlic","repo_kind":"official","path":"MLIC++/modules/layers/conv.py","file_url":"https://github.com/jiangweibeta/mlic/blob/HEAD/MLIC%2B%2B/modules/layers/conv.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1afd37c576493fea"}},{"code_sha256_prefix":"5a29788883044d22","entry":"build_position_index","repo":"jiangweibeta/mlic","repo_kind":"official","path":"MLIC++/modules/layers/attention.py","file_url":"https://github.com/jiangweibeta/mlic/blob/HEAD/MLIC%2B%2B/modules/layers/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5a29788883044d22"}},{"code_sha256_prefix":"15eae621014906be","entry":"conv1x1","repo":"jiangweibeta/mlic","repo_kind":"official","path":"MLIC++/modules/layers/conv.py","file_url":"https://github.com/jiangweibeta/mlic/blob/HEAD/MLIC%2B%2B/modules/layers/conv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"15eae621014906be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}