{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/image-matting","name":"Image Matting","slug":"image-matting","description_markdown":"**Image Matting** is the process of accurately estimating the foreground object in images and videos. It is a very important technique in image and video editing applications, particularly in film production for creating visual effects. In case of image segmentation, we segment the image into foreground and background by labeling the pixels. Image segmentation generates a binary image, in which a pixel either belongs to foreground or background. However, Image Matting is different from the image segmentation, wherein some pixels may belong to foreground as well as background, such pixels are called partial or mixed pixels. In order to fully separate the foreground from the background in an image, accurate estimation of the alpha values for partial or mixed pixels is necessary.\r\n\r\n\r\n<span class=\"description-source\">Source: [Automatic Trimap Generation for Image Matting ](https://arxiv.org/abs/1707.00333)</span>\r\n\r\n<span class=\"description-source\">Image Source: [Real-Time High-Resolution Background Matting](https://arxiv.org/pdf/2012.07810v1.pdf)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":225,"papers_with_code":110,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":8,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/image-matting-on-composition-1k-1","slug":"image-matting-on-composition-1k-1","dataset":"Composition-1K","dataset_url":"/dataset/composition-1k","rows_in_archive":13,"metrics":["MSE","SAD","Conn","Grad"],"first_row_in_archive_order":{"model":"DiffMatte","paper_title":"Diffusion for Natural Image Matting","paper_url":"/paper/diffusion-for-natural-image-matting","paper_date":"2023-12-10","arxiv_id":"2312.05915","code_links":[{"title":"yihanhu-2022/diffmatte","url":"https://github.com/yihanhu-2022/diffmatte"}],"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-for-natural-image-matting#ran","syntology_url":"https://syntology.ai/paper/2312.05915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05915"}},"official":{"repos":["yihanhu-2022/diffmatte"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-matting-on-am-2k","slug":"image-matting-on-am-2k","dataset":"AM-2K","dataset_url":"/dataset/am-2k","rows_in_archive":9,"metrics":["SAD","MSE","MAD"],"first_row_in_archive_order":{"model":"StyleMatte","paper_title":"Adversarially-Guided Portrait Matting","paper_url":"/paper/adversarially-guided-portrait-matting","paper_date":"2023-05-04","arxiv_id":"2305.02981","code_links":[{"title":"chroneus/stylematte","url":"https://github.com/chroneus/stylematte"}],"syntology":null}},{"leaderboard":"/sota/image-matting-on-p3m-10k","slug":"image-matting-on-p3m-10k","dataset":"P3M-10k","dataset_url":"/dataset/p3m-10k","rows_in_archive":7,"metrics":["SAD","MSE","MAD"],"first_row_in_archive_order":{"model":"P3M-Net (v)","paper_title":"Rethinking Portrait Matting with Privacy Preserving","paper_url":"/paper/rethinking-portrait-matting-with-privacy","paper_date":"2022-03-31","arxiv_id":"2203.16828","code_links":[{"title":"vitae-transformer/p3m-net","url":"https://github.com/vitae-transformer/p3m-net"}],"syntology":null}},{"leaderboard":"/sota/image-matting-on-aim-500","slug":"image-matting-on-aim-500","dataset":"AIM-500","dataset_url":"/dataset/aim-500","rows_in_archive":6,"metrics":["SAD","MSE","MAD","Conn.","Grad."],"first_row_in_archive_order":{"model":"DiffMatte","paper_title":"Diffusion for Natural Image Matting","paper_url":"/paper/diffusion-for-natural-image-matting","paper_date":"2023-12-10","arxiv_id":"2312.05915","code_links":[{"title":"yihanhu-2022/diffmatte","url":"https://github.com/yihanhu-2022/diffmatte"}],"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-for-natural-image-matting#ran","syntology_url":"https://syntology.ai/paper/2312.05915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05915"}},"official":{"repos":["yihanhu-2022/diffmatte"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-matting-on-adobe-matting","slug":"image-matting-on-adobe-matting","dataset":"Adobe Matting","dataset_url":null,"rows_in_archive":4,"metrics":["MSE","SAD"],"first_row_in_archive_order":{"model":"Adobe LS-GAN","paper_title":"Background Matting: The World is Your Green Screen","paper_url":"/paper/background-matting-the-world-is-your-green","paper_date":"2020-04-01","arxiv_id":"2004.00626","code_links":[{"title":"senguptaumd/Background-Matting","url":"https://github.com/senguptaumd/Background-Matting"}],"syntology":null}},{"leaderboard":"/sota/image-matting-on-distinctions-646","slug":"image-matting-on-distinctions-646","dataset":"Distinctions-646","dataset_url":"/dataset/distinctions-646","rows_in_archive":4,"metrics":["SAD","MSE","Grad","Conn","Trimap"],"first_row_in_archive_order":{"model":"DiffMatte","paper_title":"Diffusion for Natural Image Matting","paper_url":"/paper/diffusion-for-natural-image-matting","paper_date":"2023-12-10","arxiv_id":"2312.05915","code_links":[{"title":"yihanhu-2022/diffmatte","url":"https://github.com/yihanhu-2022/diffmatte"}],"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-for-natural-image-matting#ran","syntology_url":"https://syntology.ai/paper/2312.05915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05915"}},"official":{"repos":["yihanhu-2022/diffmatte"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-matting-on-amd","slug":"image-matting-on-amd","dataset":"AMD","dataset_url":null,"rows_in_archive":1,"metrics":["MAD","MSE"],"first_row_in_archive_order":{"model":"MODNet+","paper_title":"MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition","paper_url":"/paper/is-a-green-screen-really-necessary-for-real","paper_date":"2020-11-24","arxiv_id":"2011.11961","code_links":[{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"ZHKKKe/MODNet","url":"https://github.com/ZHKKKe/MODNet"},{"title":"royshil/obs-backgroundremoval","url":"https://github.com/royshil/obs-backgroundremoval"},{"title":"ZHKKKe/PPM","url":"https://github.com/ZHKKKe/PPM"},{"title":"DeepranjanG/Image_Background_Removal","url":"https://github.com/DeepranjanG/Image_Background_Removal"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/MODNet"},{"title":"Mind23-2/MindCode-101","url":"https://github.com/Mind23-2/MindCode-101/tree/main/MODNet"},{"title":"MS-Mind/MS-Code-08","url":"https://github.com/MS-Mind/MS-Code-08/tree/main/MODNet"},{"title":"code-implementation1/Code5","url":"https://github.com/code-implementation1/Code5/tree/main/MODNet"}],"syntology":null}},{"leaderboard":"/sota/image-matting-on-phm-100","slug":"image-matting-on-phm-100","dataset":"PPM-100","dataset_url":"/dataset/phm-100","rows_in_archive":1,"metrics":["MAD","MSE"],"first_row_in_archive_order":{"model":"MODNet+ (Our)","paper_title":"MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition","paper_url":"/paper/is-a-green-screen-really-necessary-for-real","paper_date":"2020-11-24","arxiv_id":"2011.11961","code_links":[{"title":"PaddlePaddle/PaddleSeg","url":"https://github.com/PaddlePaddle/PaddleSeg"},{"title":"ZHKKKe/MODNet","url":"https://github.com/ZHKKKe/MODNet"},{"title":"royshil/obs-backgroundremoval","url":"https://github.com/royshil/obs-backgroundremoval"},{"title":"ZHKKKe/PPM","url":"https://github.com/ZHKKKe/PPM"},{"title":"DeepranjanG/Image_Background_Removal","url":"https://github.com/DeepranjanG/Image_Background_Removal"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/MODNet"},{"title":"Mind23-2/MindCode-101","url":"https://github.com/Mind23-2/MindCode-101/tree/main/MODNet"},{"title":"MS-Mind/MS-Code-08","url":"https://github.com/MS-Mind/MS-Code-08/tree/main/MODNet"},{"title":"code-implementation1/Code5","url":"https://github.com/code-implementation1/Code5/tree/main/MODNet"}],"syntology":null}}],"datasets":[{"url":"/dataset/composition-1k","name":"Composition-1K","full_name":"","num_papers_in_archive":57},{"url":"/dataset/aim-500","name":"AIM-500","full_name":"Automatic Image Matting-500","num_papers_in_archive":23},{"url":"/dataset/distinctions-646","name":"Distinctions-646","full_name":"","num_papers_in_archive":19},{"url":"/dataset/agriculture-vision","name":"Agriculture-Vision","full_name":"","num_papers_in_archive":18},{"url":"/dataset/p3m-10k","name":"P3M-10k","full_name":"Privacy-Preserving Portrait Matting Dataset","num_papers_in_archive":12},{"url":"/dataset/phm-100","name":"PPM-100","full_name":"","num_papers_in_archive":9},{"url":"/dataset/am-2k","name":"AM-2K","full_name":"Animal Matting 2,000 Dataset","num_papers_in_archive":6},{"url":"/dataset/withoutbg100-dataset","name":"withoutbg100 dataset","full_name":"withoutbg100 Dataset for Image Matting","num_papers_in_archive":0}],"subtasks":[{"url":"/task/semantic-image-matting","name":"Semantic Image Matting"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":3,"rows_per_page":100,"shown":100,"of":225,"of_with_code":110,"tagged_in_all":225,"counts":{"archive_papers_tagged":225,"with_a_code_link":110,"where_syntology_ran_a_sample":21,"not_listed_spam_title":0,"listed":225,"listed_where_code_ran":21,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":15,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":15,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/vitmatte-boosting-image-matting-with","slug":"vitmatte-boosting-image-matting-with","title":"ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers","date":"2023-05-24","arxiv_id":"2305.15272","repositories_listed":9,"syntology":null},{"url":"/paper/is-a-green-screen-really-necessary-for-real","slug":"is-a-green-screen-really-necessary-for-real","title":"MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition","date":"2020-11-24","arxiv_id":"2011.11961","repositories_listed":9,"syntology":null},{"url":"/paper/deep-image-matting","slug":"deep-image-matting","title":"Deep Image Matting","date":"2017-03-10","arxiv_id":"1703.03872","repositories_listed":8,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/deep-image-matting#ran","syntology_url":"https://syntology.ai/paper/1703.03872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.03872"}},"official":null}},{"url":"/paper/index-network","slug":"index-network","title":"Index Network","date":"2019-08-11","arxiv_id":"1908.09895","repositories_listed":6,"syntology":null},{"url":"/paper/towards-ghost-free-shadow-removal-via-dual","slug":"towards-ghost-free-shadow-removal-via-dual","title":"Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN","date":"2019-11-20","arxiv_id":"1911.08718","repositories_listed":5,"syntology":null},{"url":"/paper/castle-in-the-sky-dynamic-sky-replacement-and","slug":"castle-in-the-sky-dynamic-sky-replacement-and","title":"Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos","date":"2020-10-22","arxiv_id":"2010.11800","repositories_listed":4,"syntology":null},{"url":"/paper/190503633","slug":"190503633","title":"Intra-frame Object Tracking by Deblatting","date":"2019-05-09","arxiv_id":"1905.03633","repositories_listed":3,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/190503633#ran","syntology_url":"https://syntology.ai/paper/1905.03633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.03633"}},"official":{"repos":["rozumden/deblatting_python"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/tom-net-learning-transparent-object-matting","slug":"tom-net-learning-transparent-object-matting","title":"TOM-Net: Learning Transparent Object Matting from a Single Image","date":"2018-03-13","arxiv_id":"1803.04636","repositories_listed":3,"syntology":null},{"url":"/paper/reflow6d-refraction-guided-transparent-object","slug":"reflow6d-refraction-guided-transparent-object","title":"ReFlow6D: Refraction-Guided Transparent Object 6D Pose Estimation via Intermediate Representation Learning","date":"2024-12-30","arxiv_id":"2412.20830","repositories_listed":2,"syntology":null},{"url":"/paper/alfie-democratising-rgba-image-generation","slug":"alfie-democratising-rgba-image-generation","title":"Alfie: Democratising RGBA Image Generation With No $$$","date":"2024-08-27","arxiv_id":"2408.14826","repositories_listed":2,"syntology":null},{"url":"/paper/on-point-affiliation-in-feature-upsampling","slug":"on-point-affiliation-in-feature-upsampling","title":"On Point Affiliation in Feature Upsampling","date":"2023-07-17","arxiv_id":"2307.08198","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/on-point-affiliation-in-feature-upsampling#ran","syntology_url":"https://syntology.ai/paper/2307.08198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08198"}},"official":{"repos":["tiny-smart/sapa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/sapa-similarity-aware-point-affiliation-for","slug":"sapa-similarity-aware-point-affiliation-for","title":"SAPA: Similarity-Aware Point Affiliation for Feature Upsampling","date":"2022-09-26","arxiv_id":"2209.12866","repositories_listed":2,"syntology":null},{"url":"/paper/deep-pcb-to-coco-convertor","slug":"deep-pcb-to-coco-convertor","title":"Deep PCB To COCO Convertor","date":"2022-05-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/privacy-preserving-portrait-matting","slug":"privacy-preserving-portrait-matting","title":"Privacy-Preserving Portrait Matting","date":"2021-04-29","arxiv_id":"2104.14222","repositories_listed":2,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/privacy-preserving-portrait-matting#ran","syntology_url":"https://syntology.ai/paper/2104.14222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14222"}},"official":{"repos":["JizhiziLi/P3M"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/real-time-high-resolution-background-matting","slug":"real-time-high-resolution-background-matting","title":"Real-Time High-Resolution Background Matting","date":"2020-12-14","arxiv_id":"2012.07810","repositories_listed":2,"syntology":null},{"url":"/paper/fast-multi-level-foreground-estimation","slug":"fast-multi-level-foreground-estimation","title":"Fast Multi-Level Foreground Estimation","date":"2020-06-26","arxiv_id":"2006.14970","repositories_listed":2,"syntology":null},{"url":"/paper/camouflaged-object-detection","slug":"camouflaged-object-detection","title":"Camouflaged Object Detection","date":"2020-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/f-b-alpha-matting","slug":"f-b-alpha-matting","title":"$F$, $B$, Alpha Matting","date":"2020-03-17","arxiv_id":"2003.07711","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/f-b-alpha-matting#ran","syntology_url":"https://syntology.ai/paper/2003.07711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07711"}},"official":null}},{"url":"/paper/sub-frame-appearance-and-6d-pose-estimation","slug":"sub-frame-appearance-and-6d-pose-estimation","title":"Sub-frame Appearance and 6D Pose Estimation of Fast Moving Objects","date":"2019-11-25","arxiv_id":"1911.10927","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/sub-frame-appearance-and-6d-pose-estimation#ran","syntology_url":"https://syntology.ai/paper/1911.10927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.10927"}},"official":{"repos":["rozumden/deblatting_python"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/non-causal-tracking-by-deblatting","slug":"non-causal-tracking-by-deblatting","title":"Non-Causal Tracking by Deblatting","date":"2019-09-15","arxiv_id":"1909.06894","repositories_listed":2,"syntology":null},{"url":"/paper/towards-real-time-automatic-portrait-matting","slug":"towards-real-time-automatic-portrait-matting","title":"Towards Real-Time Automatic Portrait Matting on Mobile Devices","date":"2019-04-08","arxiv_id":"1904.03816","repositories_listed":2,"syntology":null},{"url":"/paper/semantic-human-matting","slug":"semantic-human-matting","title":"Semantic Human Matting","date":"2018-09-05","arxiv_id":"1809.01354","repositories_listed":2,"syntology":null},{"url":"/paper/real-time-deep-hair-matting-on-mobile-devices","slug":"real-time-deep-hair-matting-on-mobile-devices","title":"Real-time deep hair matting on mobile devices","date":"2017-12-19","arxiv_id":"1712.07168","repositories_listed":2,"syntology":null},{"url":"/paper/mass13k-a-matting-level-semantic-segmentation","slug":"mass13k-a-matting-level-semantic-segmentation","title":"MaSS13K: A Matting-level Semantic Segmentation Benchmark","date":"2025-03-24","arxiv_id":"2503.18364","repositories_listed":1,"syntology":null},{"url":"/paper/vrmdiff-text-guided-video-referring-matting","slug":"vrmdiff-text-guided-video-referring-matting","title":"VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion","date":"2025-03-11","arxiv_id":"2503.10678","repositories_listed":1,"syntology":null},{"url":"/paper/ben-using-confidence-guided-matting-for","slug":"ben-using-confidence-guided-matting-for","title":"BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation","date":"2025-01-08","arxiv_id":"2501.06230","repositories_listed":1,"syntology":null},{"url":"/paper/memory-efficient-matting-with-adaptive-token","slug":"memory-efficient-matting-with-adaptive-token","title":"Memory Efficient Matting with Adaptive Token Routing","date":"2024-12-14","arxiv_id":"2412.10702","repositories_listed":1,"syntology":null},{"url":"/paper/zim-zero-shot-image-matting-for-anything","slug":"zim-zero-shot-image-matting-for-anything","title":"ZIM: Zero-Shot Image Matting for Anything","date":"2024-11-01","arxiv_id":"2411.00626","repositories_listed":1,"syntology":null},{"url":"/paper/dfimat-decoupled-flexible-interactive-matting","slug":"dfimat-decoupled-flexible-interactive-matting","title":"DFIMat: Decoupled Flexible Interactive Matting in Multi-Person Scenarios","date":"2024-10-13","arxiv_id":"2410.09788","repositories_listed":1,"syntology":null},{"url":"/paper/towards-natural-image-matting-in-the-wild-via","slug":"towards-natural-image-matting-in-the-wild-via","title":"Towards Natural Image Matting in the Wild via Real-Scenario Prior","date":"2024-10-09","arxiv_id":"2410.06593","repositories_listed":1,"syntology":null},{"url":"/paper/training-matting-models-without-alpha-labels","slug":"training-matting-models-without-alpha-labels","title":"Training Matting Models without Alpha Labels","date":"2024-08-20","arxiv_id":"2408.10539","repositories_listed":1,"syntology":null},{"url":"/paper/fade-a-task-agnostic-upsampling-operator-for","slug":"fade-a-task-agnostic-upsampling-operator-for","title":"FADE: A Task-Agnostic Upsampling Operator for Encoder-Decoder Architectures","date":"2024-07-18","arxiv_id":"2407.13500","repositories_listed":1,"syntology":null},{"url":"/paper/maggie-masked-guided-gradual-human-instance","slug":"maggie-masked-guided-gradual-human-instance","title":"MaGGIe: Masked Guided Gradual Human Instance Matting","date":"2024-04-24","arxiv_id":"2404.16035","repositories_listed":1,"syntology":null},{"url":"/paper/learning-trimaps-via-clicks-for-image-matting","slug":"learning-trimaps-via-clicks-for-image-matting","title":"Learning Trimaps via Clicks for Image Matting","date":"2024-03-30","arxiv_id":"2404.00335","repositories_listed":1,"syntology":null},{"url":"/paper/in-context-matting","slug":"in-context-matting","title":"In-Context Matting","date":"2024-03-23","arxiv_id":"2403.15789","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-models-trained-with-large-data-are","slug":"diffusion-models-trained-with-large-data-are","title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?","date":"2024-03-10","arxiv_id":"2403.06090","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffusion-models-trained-with-large-data-are#ran","syntology_url":"https://syntology.ai/paper/2403.06090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06090"}},"official":{"repos":["aim-uofa/genpercept"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/end-to-end-human-instance-matting","slug":"end-to-end-human-instance-matting","title":"End-to-End Human Instance Matting","date":"2024-03-03","arxiv_id":"2403.01510","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-human-instance-matting#ran","syntology_url":"https://syntology.ai/paper/2403.01510","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01510"}},"official":{"repos":["qlyoo/e2e-him"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dual-context-aggregation-for-universal-image","slug":"dual-context-aggregation-for-universal-image","title":"Dual-Context Aggregation for Universal Image Matting","date":"2024-02-28","arxiv_id":"2402.18109","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-automatic-and-interactive-matting","slug":"unifying-automatic-and-interactive-matting","title":"Unifying Automatic and Interactive Matting with Pretrained ViTs","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-for-natural-image-matting","slug":"diffusion-for-natural-image-matting","title":"Diffusion for Natural Image Matting","date":"2023-12-10","arxiv_id":"2312.05915","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-for-natural-image-matting#ran","syntology_url":"https://syntology.ai/paper/2312.05915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05915"}},"official":{"repos":["yihanhu-2022/diffmatte"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/video-instance-matting","slug":"video-instance-matting","title":"Video Instance Matting","date":"2023-11-07","arxiv_id":"2311.04212","repositories_listed":1,"syntology":null},{"url":"/paper/omnimatterf-robust-omnimatte-with-3d","slug":"omnimatterf-robust-omnimatte-with-3d","title":"OmnimatteRF: Robust Omnimatte with 3D Background Modeling","date":"2023-09-14","arxiv_id":"2309.07749","repositories_listed":1,"syntology":null},{"url":"/paper/matting-anything","slug":"matting-anything","title":"Matting Anything","date":"2023-06-08","arxiv_id":"2306.05399","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/matting-anything#ran","syntology_url":"https://syntology.ai/paper/2306.05399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05399"}},"official":{"repos":["shi-labs/matting-anything"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/matte-anything-interactive-natural-image","slug":"matte-anything-interactive-natural-image","title":"Matte Anything: Interactive Natural Image Matting with Segment Anything Models","date":"2023-06-07","arxiv_id":"2306.04121","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/matte-anything-interactive-natural-image#ran","syntology_url":"https://syntology.ai/paper/2306.04121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04121"}},"official":{"repos":["hustvl/matte-anything"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dugmatting-decomposed-uncertainty-guided","slug":"dugmatting-decomposed-uncertainty-guided","title":"dugMatting: Decomposed-Uncertainty-Guided Matting","date":"2023-06-02","arxiv_id":"2306.01452","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/dugmatting-decomposed-uncertainty-guided#ran","syntology_url":"https://syntology.ai/paper/2306.01452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01452"}},"official":{"repos":["fire-friend/dugmatting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/renderme-360-a-large-digital-asset-library-1","slug":"renderme-360-a-large-digital-asset-library-1","title":"RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars","date":"2023-05-22","arxiv_id":"2305.13353","repositories_listed":1,"syntology":null},{"url":"/paper/adversarially-guided-portrait-matting","slug":"adversarially-guided-portrait-matting","title":"Adversarially-Guided Portrait Matting","date":"2023-05-04","arxiv_id":"2305.02981","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-human-matting-for-dynamic-videos","slug":"adaptive-human-matting-for-dynamic-videos","title":"Adaptive Human Matting for Dynamic Videos","date":"2023-04-12","arxiv_id":"2304.06018","repositories_listed":1,"syntology":null},{"url":"/paper/deep-image-matting-a-comprehensive-survey","slug":"deep-image-matting-a-comprehensive-survey","title":"Deep Image Matting: A Comprehensive Survey","date":"2023-04-10","arxiv_id":"2304.04672","repositories_listed":1,"syntology":null},{"url":"/paper/disentangled-pre-training-for-image-matting","slug":"disentangled-pre-training-for-image-matting","title":"Disentangled Pre-training for Image Matting","date":"2023-04-03","arxiv_id":"2304.00784","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-context-aggregation-in-natural","slug":"rethinking-context-aggregation-in-natural","title":"Revisiting Context Aggregation for Image Matting","date":"2023-04-03","arxiv_id":"2304.01171","repositories_listed":1,"syntology":null},{"url":"/paper/cap-vstnet-content-affinity-preserved","slug":"cap-vstnet-content-affinity-preserved","title":"CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer","date":"2023-03-31","arxiv_id":"2303.17867","repositories_listed":1,"syntology":null},{"url":"/paper/transmatting-tri-token-equipped-transformer","slug":"transmatting-tri-token-equipped-transformer","title":"TransMatting: Tri-token Equipped Transformer Model for Image Matting","date":"2023-03-11","arxiv_id":"2303.06476","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-video-matting-with-trimap","slug":"end-to-end-video-matting-with-trimap","title":"End-to-End Video Matting With Trimap Propagation","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ultrahigh-resolution-image-video-matting-with","slug":"ultrahigh-resolution-image-video-matting-with","title":"Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/infusing-definiteness-into-randomness","slug":"infusing-definiteness-into-randomness","title":"Infusing Definiteness into Randomness: Rethinking Composition Styles for Deep Image Matting","date":"2022-12-27","arxiv_id":"2212.13517","repositories_listed":1,"syntology":null},{"url":"/paper/lightweight-alpha-matting-network-using","slug":"lightweight-alpha-matting-network-using","title":"Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning","date":"2022-10-14","arxiv_id":"2210.07760","repositories_listed":1,"syntology":null},{"url":"/paper/robust-human-matting-via-semantic-guidance","slug":"robust-human-matting-via-semantic-guidance","title":"Robust Human Matting via Semantic Guidance","date":"2022-10-11","arxiv_id":"2210.05210","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-matting-specific-portrait","slug":"self-supervised-matting-specific-portrait","title":"Self-supervised Matting-specific Portrait Enhancement and Generation","date":"2022-08-13","arxiv_id":"2208.06601","repositories_listed":1,"syntology":null},{"url":"/paper/transmatting-enhancing-transparent-objects","slug":"transmatting-enhancing-transparent-objects","title":"TransMatting: Enhancing Transparent Objects Matting with Transformers","date":"2022-08-05","arxiv_id":"2208.03007","repositories_listed":1,"syntology":null},{"url":"/paper/one-trimap-video-matting","slug":"one-trimap-video-matting","title":"One-Trimap Video Matting","date":"2022-07-27","arxiv_id":"2207.13353","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/one-trimap-video-matting#ran","syntology_url":"https://syntology.ai/paper/2207.13353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.13353"}},"official":{"repos":["hongje/otvm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/fade-fusing-the-assets-of-decoder-and-encoder","slug":"fade-fusing-the-assets-of-decoder-and-encoder","title":"FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling","date":"2022-07-21","arxiv_id":"2207.10392","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fade-fusing-the-assets-of-decoder-and-encoder#ran","syntology_url":"https://syntology.ai/paper/2207.10392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10392"}},"official":null}},{"url":"/paper/referring-image-matting","slug":"referring-image-matting","title":"Referring Image Matting","date":"2022-06-10","arxiv_id":"2206.05149","repositories_listed":1,"syntology":null},{"url":"/paper/human-instance-matting-via-mutual-guidance","slug":"human-instance-matting-via-mutual-guidance","title":"Human Instance Matting via Mutual Guidance and Multi-Instance Refinement","date":"2022-05-22","arxiv_id":"2205.10767","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/human-instance-matting-via-mutual-guidance#ran","syntology_url":"https://syntology.ai/paper/2205.10767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10767"}},"official":{"repos":["nowsyn/instmatt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unified-interactive-image-matting","slug":"unified-interactive-image-matting","title":"Exploring the Interactive Guidance for Unified and Effective Image Matting","date":"2022-05-17","arxiv_id":"2205.08324","repositories_listed":1,"syntology":null},{"url":"/paper/augmented-balanced-image-dataset-generator","slug":"augmented-balanced-image-dataset-generator","title":"Augmented Balanced Image Dataset Generator Using AugStatic Library","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/augstatic-a-light-weight-image-augmentation","slug":"augstatic-a-light-weight-image-augmentation","title":"AugStatic - A Light-Weight Image Augmentation Library","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exposure-correction-model-to-enhance-image","slug":"exposure-correction-model-to-enhance-image","title":"Exposure Correction Model to Enhance Image Quality","date":"2022-04-22","arxiv_id":"2204.10648","repositories_listed":1,"syntology":null},{"url":"/paper/pp-matting-high-accuracy-natural-image","slug":"pp-matting-high-accuracy-natural-image","title":"PP-Matting: High-Accuracy Natural Image Matting","date":"2022-04-20","arxiv_id":"2204.09433","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-portrait-matting-with-privacy","slug":"rethinking-portrait-matting-with-privacy","title":"Rethinking Portrait Matting with Privacy Preserving","date":"2022-03-31","arxiv_id":"2203.16828","repositories_listed":1,"syntology":null},{"url":"/paper/matteformer-transformer-based-image-matting","slug":"matteformer-transformer-based-image-matting","title":"MatteFormer: Transformer-Based Image Matting via Prior-Tokens","date":"2022-03-29","arxiv_id":"2203.15662","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/matteformer-transformer-based-image-matting#ran","syntology_url":"https://syntology.ai/paper/2203.15662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15662"}},"official":{"repos":["webtoon/matteformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/improving-deep-image-matting-via-local","slug":"improving-deep-image-matting-via-local","title":"Improving Deep Image Matting via Local Smoothness Assumption","date":"2021-12-27","arxiv_id":"2112.13809","repositories_listed":1,"syntology":null},{"url":"/paper/trimap-guided-feature-mining-and-fusion","slug":"trimap-guided-feature-mining-and-fusion","title":"Trimap-guided Feature Mining and Fusion Network for Natural Image Matting","date":"2021-12-01","arxiv_id":"2112.00510","repositories_listed":1,"syntology":null},{"url":"/paper/deep-image-matting-with-flexible-guidance","slug":"deep-image-matting-with-flexible-guidance","title":"Deep Image Matting with Flexible Guidance Input","date":"2021-10-21","arxiv_id":"2110.10898","repositories_listed":1,"syntology":null},{"url":"/paper/virtual-multi-modality-self-supervised-1","slug":"virtual-multi-modality-self-supervised-1","title":"Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction","date":"2021-10-07","arxiv_id":"2110.03278","repositories_listed":1,"syntology":null},{"url":"/paper/long-range-feature-propagating-for-natural","slug":"long-range-feature-propagating-for-natural","title":"Long-Range Feature Propagating for Natural Image Matting","date":"2021-09-25","arxiv_id":"2109.12252","repositories_listed":1,"syntology":null},{"url":"/paper/modnet-v-improving-portrait-video-matting-via","slug":"modnet-v-improving-portrait-video-matting-via","title":"MODNet-V: Improving Portrait Video Matting via Background Restoration","date":"2021-09-24","arxiv_id":"2109.11818","repositories_listed":1,"syntology":null},{"url":"/paper/robust-high-resolution-video-matting-with","slug":"robust-high-resolution-video-matting-with","title":"Robust High-Resolution Video Matting with Temporal Guidance","date":"2021-08-25","arxiv_id":"2108.11515","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-high-resolution-video-matting-with#ran","syntology_url":"https://syntology.ai/paper/2108.11515","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.11515"}},"official":{"repos":["PeterL1n/RobustVideoMatting"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-automatic-natural-image-matting","slug":"deep-automatic-natural-image-matting","title":"Deep Automatic Natural Image Matting","date":"2021-07-15","arxiv_id":"2107.07235","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deep-automatic-natural-image-matting#ran","syntology_url":"https://syntology.ai/paper/2107.07235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07235"}},"official":{"repos":["JizhiziLi/AIM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/medical-matting-a-new-perspective-on-medical","slug":"medical-matting-a-new-perspective-on-medical","title":"Medical Matting: A New Perspective on Medical Segmentation with Uncertainty","date":"2021-06-18","arxiv_id":"2106.09887","repositories_listed":1,"syntology":null},{"url":"/paper/attention-guided-temporal-coherent-video","slug":"attention-guided-temporal-coherent-video","title":"Attention-guided Temporally Coherent Video Object Matting","date":"2021-05-24","arxiv_id":"2105.11427","repositories_listed":1,"syntology":null},{"url":"/paper/deep-video-matting-via-spatio-temporal","slug":"deep-video-matting-via-spatio-temporal","title":"Deep Video Matting via Spatio-Temporal Alignment and Aggregation","date":"2021-04-22","arxiv_id":"2104.11208","repositories_listed":1,"syntology":null},{"url":"/paper/flow-based-video-segmentation-for-human-head","slug":"flow-based-video-segmentation-for-human-head","title":"Flow-based Video Segmentation for Human Head and Shoulders","date":"2021-04-20","arxiv_id":"2104.09752","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-image-matting","slug":"semantic-image-matting","title":"Semantic Image Matting","date":"2021-04-16","arxiv_id":"2104.08201","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/semantic-image-matting#ran","syntology_url":"https://syntology.ai/paper/2104.08201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08201"}},"official":{"repos":["nowsyn/SIM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/plade-net-towards-pixel-level-accuracy-for","slug":"plade-net-towards-pixel-level-accuracy-for","title":"PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Loss","date":"2021-03-12","arxiv_id":"2103.07362","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/plade-net-towards-pixel-level-accuracy-for#ran","syntology_url":"https://syntology.ai/paper/2103.07362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07362"}},"official":{"repos":["JuanLuisGonzalez/PLADE-net"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tripartite-information-mining-and-integration","slug":"tripartite-information-mining-and-integration","title":"Tripartite Information Mining and Integration for Image Matting","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fmodetect-robust-detection-and-trajectory","slug":"fmodetect-robust-detection-and-trajectory","title":"FMODetect: Robust Detection of Fast Moving Objects","date":"2020-12-15","arxiv_id":"2012.08216","repositories_listed":1,"syntology":null},{"url":"/paper/mask-guided-matting-via-progressive","slug":"mask-guided-matting-via-progressive","title":"Mask Guided Matting via Progressive Refinement Network","date":"2020-12-12","arxiv_id":"2012.06722","repositories_listed":1,"syntology":null},{"url":"/paper/learning-affinity-aware-upsampling-for-deep","slug":"learning-affinity-aware-upsampling-for-deep","title":"Learning Affinity-Aware Upsampling for Deep Image Matting","date":"2020-11-29","arxiv_id":"2011.14288","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-affinity-aware-upsampling-for-deep#ran","syntology_url":"https://syntology.ai/paper/2011.14288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.14288"}},"official":null}},{"url":"/paper/end-to-end-animal-image-matting","slug":"end-to-end-animal-image-matting","title":"Bridging Composite and Real: Towards End-to-end Deep Image Matting","date":"2020-10-30","arxiv_id":"2010.16188","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-animal-image-matting#ran","syntology_url":"https://syntology.ai/paper/2010.16188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.16188"}},"official":{"repos":["JizhiziLi/GFM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/attention-transfer-network-for-nature-image","slug":"attention-transfer-network-for-nature-image","title":"Attention Transfer Network for Nature Image Matting","date":"2020-09-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/guided-collaborative-training-for-pixel-wise-1","slug":"guided-collaborative-training-for-pixel-wise-1","title":"Guided Collaborative Training for Pixel-wise Semi-Supervised Learning","date":"2020-08-12","arxiv_id":"2008.05258","repositories_listed":1,"syntology":null},{"url":"/paper/jit-masker-efficient-online-distillation-for","slug":"jit-masker-efficient-online-distillation-for","title":"JIT-Masker: Efficient Online Distillation for Background Matting","date":"2020-06-11","arxiv_id":"2006.06185","repositories_listed":1,"syntology":null},{"url":"/paper/attention-guided-hierarchical-structure","slug":"attention-guided-hierarchical-structure","title":"Attention-Guided Hierarchical Structure Aggregation for Image Matting","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gimp-ml-python-plugins-for-using-computer","slug":"gimp-ml-python-plugins-for-using-computer","title":"GIMP-ML: Python Plugins for using Computer Vision Models in GIMP","date":"2020-04-27","arxiv_id":"2004.13060","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-semantic-human-matting-with-coarse","slug":"boosting-semantic-human-matting-with-coarse","title":"Boosting Semantic Human Matting with Coarse Annotations","date":"2020-04-10","arxiv_id":"2004.04955","repositories_listed":1,"syntology":null},{"url":"/paper/background-matting-the-world-is-your-green","slug":"background-matting-the-world-is-your-green","title":"Background Matting: The World is Your Green Screen","date":"2020-04-01","arxiv_id":"2004.00626","repositories_listed":1,"syntology":null},{"url":"/paper/pymatting-a-python-library-for-alpha-matting","slug":"pymatting-a-python-library-for-alpha-matting","title":"PyMatting: A Python Library for Alpha Matting","date":"2020-03-25","arxiv_id":"2003.12382","repositories_listed":1,"syntology":null},{"url":"/paper/natural-image-matting-via-guided-contextual","slug":"natural-image-matting-via-guided-contextual","title":"Natural Image Matting via Guided Contextual Attention","date":"2020-01-13","arxiv_id":"2001.04069","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/natural-image-matting-via-guided-contextual#ran","syntology_url":"https://syntology.ai/paper/2001.04069","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.04069"}},"official":{"repos":["Yaoyi-Li/GCA-Matting"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/190909725","slug":"190909725","title":"Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation","date":"2019-09-20","arxiv_id":"1909.09725","repositories_listed":1,"syntology":null}],"syntology_records":23,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/image-matting-on-am-2k","since_archive":"/sota/image-matting-on-am-2k#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/image-matting-on-aim-500","since_archive":"/sota/image-matting-on-aim-500#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":21,"papers_where_code_ran_first_page":"/task/image-matting/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":3,"url":"/task/image-matting/papers/2","json":"/task/image-matting/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/image-matting/papers/3","json":"/task/image-matting/papers/3.json","rows":25},{"order":"ran","page":1,"of":1,"url":"/task/image-matting/papers/ran/1","json":"/task/image-matting/papers/ran/1.json","rows":21}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"bb2eca487cd21e5fae0b92a914dc8e558bd8697a1a1a4cca8d2445fa6ad9fa63","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}