{"url":"/sota/image-compression-on-kodak","task":{"name":"Image Compression","url":"/task/image-compression","note":null},"dataset":{"name":"kodak","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Image Compression** is an application of data compression for digital images to lower their storage and/or transmission requirements.\r\n\r\n\r\n<span class=\"description-source\">Source: [Variable Rate Deep Image Compression With a Conditional Autoencoder ](https://arxiv.org/abs/1909.04802)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["BD-Rate over VTM-17.0"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"BD-Rate over VTM-17.0":null}},"counts":{"rows":8,"rows_with_code":8,"rows_with_paper_page":8,"rows_dated":8,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MLIC+","metrics":{"BD-Rate over VTM-17.0":"-11.39"},"uses_additional_data":false,"paper_date":"2022-11-14","paper":"/paper/multi-reference-entropy-model-for-learned","paper_url":"https://arxiv.org/abs/2211.07273v9","paper_title":"MLIC: Multi-Reference Entropy Model for Learned Image Compression","code":"https://github.com/jiangweibeta/mlic","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"MLIC++","metrics":{"BD-Rate over VTM-17.0":"-13.39"},"uses_additional_data":false,"paper_date":"2023-07-28","paper":"/paper/mlic-linear-complexity-multi-reference","paper_url":"https://arxiv.org/abs/2307.15421v9","paper_title":"MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression","code":"https://github.com/jiangweibeta/mlic","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"MLIC","metrics":{"BD-Rate over VTM-17.0":"-8.05"},"uses_additional_data":false,"paper_date":"2022-11-14","paper":"/paper/multi-reference-entropy-model-for-learned","paper_url":"https://arxiv.org/abs/2211.07273v9","paper_title":"MLIC: Multi-Reference Entropy Model for Learned Image Compression","code":"https://github.com/jiangweibeta/mlic","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"LIC-TCM Large","metrics":{"BD-Rate over VTM-17.0":"-10.14"},"uses_additional_data":false,"paper_date":"2023-03-27","paper":"/paper/learned-image-compression-with-mixed","paper_url":"https://arxiv.org/abs/2303.14978v1","paper_title":"Learned Image Compression with Mixed Transformer-CNN Architectures","code":"https://github.com/jmliu206/lic_tcm","n_code_links":3,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"ELIC","metrics":{"BD-Rate over VTM-17.0":"-5.95"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/elic-efficient-learned-image-compression-with","paper_url":"https://arxiv.org/abs/2203.10886v2","paper_title":"ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding","code":"https://github.com/VincentChandelier/ELiC-ReImplemetation","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":4,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"WACNN","metrics":{"BD-Rate over VTM-17.0":"-2.95"},"uses_additional_data":false,"paper_date":"2022-03-16","paper":"/paper/the-devil-is-in-the-details-window-based","paper_url":"https://arxiv.org/abs/2203.08450v1","paper_title":"The Devil Is in the Details: Window-based Attention for Image Compression","code":"https://github.com/googolxx/stf","n_code_links":2,"syntology":{"n_ran":11,"n_unverified":4,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"STF","metrics":{"BD-Rate over VTM-17.0":"-2.48"},"uses_additional_data":false,"paper_date":"2022-03-16","paper":"/paper/the-devil-is-in-the-details-window-based","paper_url":"https://arxiv.org/abs/2203.08450v1","paper_title":"The Devil Is in the Details: Window-based Attention for Image Compression","code":"https://github.com/googolxx/stf","n_code_links":2,"syntology":{"n_ran":11,"n_unverified":4,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"SegPIC","metrics":{"BD-Rate over VTM-17.0":"-8.18"},"uses_additional_data":false,"paper_date":"2024-03-01","paper":"/paper/region-adaptive-transform-with-segmentation","paper_url":"https://arxiv.org/abs/2403.00628v4","paper_title":"Region-Adaptive Transform with Segmentation Prior for Image Compression","code":"https://github.com/gityuxiliu/segpic-for-image-compression","n_code_links":2,"syntology":{"n_ran":14,"n_unverified":4,"n_samples":18,"n_pointer_only_licence":18}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":6,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":41,"n_unverified":17,"n_samples":58,"n_pointer_only_licence":18,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":52,"n_unverified":21,"n_samples":73,"n_pointer_only_licence":18,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}