{"url":"/task/image-manipulation-localization","name":"Image Manipulation Localization","slug":"image-manipulation-localization","description_markdown":"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.","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":31,"papers_with_code":16,"benchmarks":9,"benchmark_tables_in_archive":9,"benchmark_tables_shown":9,"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":6,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/image-manipulation-localization-on-casia-v1","slug":"image-manipulation-localization-on-casia-v1","dataset":"Casia V1+","dataset_url":"/dataset/casia-v1","rows_in_archive":11,"metrics":["Average Pixel F1(Fixed threshold)"],"first_row_in_archive_order":{"model":"CMX (RGB+SRM)","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","paper_url":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","paper_date":"2022-03-09","arxiv_id":"2203.04838","code_links":[{"title":"huaaaliu/rgbx_semantic_segmentation","url":"https://github.com/huaaaliu/rgbx_semantic_segmentation"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/image-manipulation-localization-on-cocoglide","slug":"image-manipulation-localization-on-cocoglide","dataset":"CocoGlide","dataset_url":null,"rows_in_archive":11,"metrics":["Average Pixel F1(Fixed threshold)"],"first_row_in_archive_order":{"model":"CMX (RGB+SRM)","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","paper_url":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","paper_date":"2022-03-09","arxiv_id":"2203.04838","code_links":[{"title":"huaaaliu/rgbx_semantic_segmentation","url":"https://github.com/huaaaliu/rgbx_semantic_segmentation"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/image-manipulation-localization-on-columbia","slug":"image-manipulation-localization-on-columbia","dataset":"Columbia","dataset_url":null,"rows_in_archive":11,"metrics":["Average Pixel F1(Fixed threshold)"],"first_row_in_archive_order":{"model":"Early Fusion","paper_title":"MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization","paper_url":"/paper/exploring-multi-modal-fusion-for-image","paper_date":"2023-12-04","arxiv_id":"2312.01790","code_links":[{"title":"idt-iti/mmfusion-iml","url":"https://github.com/idt-iti/mmfusion-iml"}],"syntology":null}},{"leaderboard":"/sota/image-manipulation-localization-on-coverage","slug":"image-manipulation-localization-on-coverage","dataset":"COVERAGE","dataset_url":"/dataset/coverage","rows_in_archive":11,"metrics":["Average Pixel F1(Fixed threshold)"],"first_row_in_archive_order":{"model":"Early Fusion","paper_title":"MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization","paper_url":"/paper/exploring-multi-modal-fusion-for-image","paper_date":"2023-12-04","arxiv_id":"2312.01790","code_links":[{"title":"idt-iti/mmfusion-iml","url":"https://github.com/idt-iti/mmfusion-iml"}],"syntology":null}},{"leaderboard":"/sota/image-manipulation-localization-on-dso-1","slug":"image-manipulation-localization-on-dso-1","dataset":"DSO-1","dataset_url":null,"rows_in_archive":11,"metrics":["Average Pixel F1(Fixed threshold)"],"first_row_in_archive_order":{"model":"TruFor","paper_title":"TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization","paper_url":"/paper/trufor-leveraging-all-round-clues-for","paper_date":"2022-12-21","arxiv_id":"2212.10957","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-manipulation-localization-on-casiav1","slug":"image-manipulation-localization-on-casiav1","dataset":"CASIAv1(Protoclo-CAT)","dataset_url":null,"rows_in_archive":8,"metrics":["Pixel Binary F1"],"first_row_in_archive_order":{"model":"Mesorch","paper_title":"Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization","paper_url":"/paper/mesoscopic-insights-orchestrating-multi-scale","paper_date":"2024-12-18","arxiv_id":"2412.13753","code_links":[{"title":"scu-zjz/Mesorch","url":"https://github.com/scu-zjz/Mesorch"}],"syntology":null}},{"leaderboard":"/sota/image-manipulation-localization-on-columbia-1","slug":"image-manipulation-localization-on-columbia-1","dataset":"Columbia(Protocol-CAT)","dataset_url":null,"rows_in_archive":8,"metrics":["Pixel Binary F1"],"first_row_in_archive_order":{"model":"IML-ViT","paper_title":"IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer","paper_url":"/paper/iml-vit-image-manipulation-localization-by","paper_date":"2023-07-27","arxiv_id":"2307.14863","code_links":[{"title":"sunnyhaze/iml-vit","url":"https://github.com/sunnyhaze/iml-vit"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/image-manipulation-localization-on-coverage-1","slug":"image-manipulation-localization-on-coverage-1","dataset":"COVERAGE(Protocol-CAT)","dataset_url":null,"rows_in_archive":8,"metrics":["Pixel Binary F1"],"first_row_in_archive_order":{"model":"IML-ViT","paper_title":"IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer","paper_url":"/paper/iml-vit-image-manipulation-localization-by","paper_date":"2023-07-27","arxiv_id":"2307.14863","code_links":[{"title":"sunnyhaze/iml-vit","url":"https://github.com/sunnyhaze/iml-vit"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/image-manipulation-localization-on-nist16","slug":"image-manipulation-localization-on-nist16","dataset":"NIST16(Protocol-CAT)","dataset_url":null,"rows_in_archive":8,"metrics":["Pixel Binary F1"],"first_row_in_archive_order":{"model":"IML-ViT","paper_title":"IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer","paper_url":"/paper/iml-vit-image-manipulation-localization-by","paper_date":"2023-07-27","arxiv_id":"2307.14863","code_links":[{"title":"sunnyhaze/iml-vit","url":"https://github.com/sunnyhaze/iml-vit"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/casia-v1","name":"Casia V1+","full_name":"","num_papers_in_archive":11},{"url":"/dataset/coverage","name":"COVERAGE","full_name":"Copy-Move Forgery Database with Similar but Genuine Objects","num_papers_in_archive":9},{"url":"/dataset/casia-osn-transmitted-weibo","name":"CASIA (OSN-transmitted - Weibo)","full_name":"","num_papers_in_archive":4},{"url":"/dataset/casia-osn-transmitted-whatsapp","name":"CASIA (OSN-transmitted - Whatsapp)","full_name":"","num_papers_in_archive":4},{"url":"/dataset/image-manipulation-dataset-df2023","name":"Digital Forensics 2023 dataset - DF2023","full_name":"","num_papers_in_archive":0},{"url":"/dataset/eren-tahir","name":"DIS100k","full_name":"DIS100k","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":16,"of":16,"tagged_in_all":31,"items":[{"url":"/paper/mantra-net-manipulation-tracing-network-for","title":"ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features","date":"2019-06-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/mvss-net-multi-view-multi-scale-supervised","title":"MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection","date":"2021-12-16","arxiv_id":"2112.08935","repositories_listed":2,"syntology":null},{"url":"/paper/image-manipulation-detection-by-multi-view","title":"Image Manipulation Detection by Multi-View Multi-Scale Supervision","date":"2021-04-14","arxiv_id":"2104.06832","repositories_listed":2,"syntology":{"n":13,"n_ran":9,"n_unverified":4,"n_pointer_only":13}},{"url":"/paper/2505-11003","title":"ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization","date":"2025-05-16","arxiv_id":"2505.11003","repositories_listed":1,"syntology":null},{"url":"/paper/can-we-get-rid-of-handcrafted-feature","title":"Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer","date":"2024-12-19","arxiv_id":"2412.14598","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/mesoscopic-insights-orchestrating-multi-scale","title":"Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization","date":"2024-12-18","arxiv_id":"2412.13753","repositories_listed":1,"syntology":null},{"url":"/paper/digital-image-forensics-a-quantitative","title":"Digital Image Forensics: A quantitative & qualitative comparison between State-of-the-art-AI and Traditional Techniques for detection and localization of image manipulations","date":"2024-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/imdl-benco-a-comprehensive-benchmark-and","title":"IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization","date":"2024-06-15","arxiv_id":"2406.10580","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/towards-modern-image-manipulation","title":"Towards Modern Image Manipulation Localization: A Large-Scale Dataset and Novel Methods","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-multi-modal-fusion-for-image","title":"MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization","date":"2023-12-04","arxiv_id":"2312.01790","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-free-image-manipulation","title":"Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learning","date":"2023-09-26","arxiv_id":"2309.14900","repositories_listed":1,"syntology":null},{"url":"/paper/iml-vit-image-manipulation-localization-by","title":"IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer","date":"2023-07-27","arxiv_id":"2307.14863","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","date":"2022-03-09","arxiv_id":"2203.04838","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/learning-jpeg-compression-artifacts-for-image","title":"Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization","date":"2021-08-30","arxiv_id":"2108.12947","repositories_listed":1,"syntology":null},{"url":"/paper/pscc-net-progressive-spatio-channel","title":"PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization","date":"2021-03-19","arxiv_id":"2103.10596","repositories_listed":1,"syntology":null},{"url":"/paper/span-spatial-pyramid-attention-network-for","title":"SPAN: Spatial Pyramid Attention Network for Image Manipulation Localization","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":5,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}