{"url":"/sota/image-manipulation-localization-on-dso-1","task":{"name":"Image Manipulation Localization","url":"/task/image-manipulation-localization","note":null},"dataset":{"name":"DSO-1","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"The task of segmenting parts of images or image parts that have been tampered with or manipulated (sometimes also referred to as doctored). This typically encompasses image splicing, copy-move, or image inpainting.","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":["Average Pixel F1(Fixed threshold)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average Pixel F1(Fixed threshold)":"higher"}},"counts":{"rows":11,"rows_with_code":9,"rows_with_paper_page":11,"rows_dated":10,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"TruFor","metrics":{"Average Pixel F1(Fixed threshold)":".930"},"uses_additional_data":false,"paper_date":"2022-12-21","paper":"/paper/trufor-leveraging-all-round-clues-for","paper_url":"https://arxiv.org/abs/2212.10957v3","paper_title":"TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Late Fusion","metrics":{"Average Pixel F1(Fixed threshold)":".899"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/exploring-multi-modal-fusion-for-image","paper_url":"https://arxiv.org/abs/2312.01790v2","paper_title":"MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization","code":"https://github.com/idt-iti/mmfusion-iml","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"CMX (RGB+NP++)","metrics":{"Average Pixel F1(Fixed threshold)":".895"},"uses_additional_data":false,"paper_date":"2022-03-09","paper":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","code":"https://github.com/huaaaliu/rgbx_semantic_segmentation","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Early Fusion","metrics":{"Average Pixel F1(Fixed threshold)":".869"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/exploring-multi-modal-fusion-for-image","paper_url":"https://arxiv.org/abs/2312.01790v2","paper_title":"MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization","code":"https://github.com/idt-iti/mmfusion-iml","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"CMX (RGB+SRM)","metrics":{"Average Pixel F1(Fixed threshold)":".792"},"uses_additional_data":false,"paper_date":"2022-03-09","paper":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","code":"https://github.com/huaaaliu/rgbx_semantic_segmentation","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"CMX (RGB+Bayar)","metrics":{"Average Pixel F1(Fixed threshold)":".776"},"uses_additional_data":false,"paper_date":"2022-03-09","paper":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","code":"https://github.com/huaaaliu/rgbx_semantic_segmentation","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"CAT-Net v2","metrics":{"Average Pixel F1(Fixed threshold)":".584"},"uses_additional_data":false,"paper_date":"2021-08-30","paper":"/paper/learning-jpeg-compression-artifacts-for-image","paper_url":"https://arxiv.org/abs/2108.12947v2","paper_title":"Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization","code":"https://github.com/mjkwon2021/cat-net","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"ManTraNet","metrics":{"Average Pixel F1(Fixed threshold)":".412"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/mantra-net-manipulation-tracing-network-for","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Wu_ManTra-Net_Manipulation_Tracing_Network_for_Detection_and_Localization_of_Image_CVPR_2019_paper.html","paper_title":"ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features","code":"https://github.com/ISICV/ManTraNet","n_code_links":3,"syntology":null},{"rank_in_archive_order":9,"model":"MVSS-Net","metrics":{"Average Pixel F1(Fixed threshold)":".358"},"uses_additional_data":false,"paper_date":"2021-04-14","paper":"/paper/image-manipulation-detection-by-multi-view","paper_url":"https://arxiv.org/abs/2104.06832v2","paper_title":"Image Manipulation Detection by Multi-View Multi-Scale Supervision","code":"https://github.com/dong03/MVSS-Net","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":13}},{"rank_in_archive_order":10,"model":"CR-CNN","metrics":{"Average Pixel F1(Fixed threshold)":".289"},"uses_additional_data":false,"paper_date":"2019-11-19","paper":"/paper/constrained-r-cnn-a-general-image","paper_url":"https://arxiv.org/abs/1911.08217v3","paper_title":"Constrained R-CNN: A general image manipulation detection model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"SPAN","metrics":{"Average Pixel F1(Fixed threshold)":".233"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/span-spatial-pyramid-attention-network-for","paper_url":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/3720_ECCV_2020_paper.php","paper_title":"SPAN: Spatial Pyramid Attention Network for Image Manipulation Localization","code":"https://github.com/ZhiHanZ/IRIS0-SPAN","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":11,"n_unverified":4,"n_samples":15,"n_pointer_only_licence":13,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":15,"n_unverified":4,"n_samples":19,"n_pointer_only_licence":13,"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"}}}