{"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/transfusion-a-transparency-based-diffusion","title":"TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection","arxiv_id":"2311.09999","date":"2023-11-16","proceeding":null,"authors":["Matic Fučka","Vitjan Zavrtanik","Danijel Skočaj"],"abstract":"Surface anomaly detection is a vital component in manufacturing inspection. Current discriminative methods follow a two-stage architecture composed of a reconstructive network followed by a discriminative network that relies on the reconstruction output. Currently used reconstructive networks often produce poor reconstructions that either still contain anomalies or lack details in anomaly-free regions. Discriminative methods are robust to some reconstructive network failures, suggesting that the discriminative network learns a strong normal appearance signal that the reconstructive networks miss. We reformulate the two-stage architecture into a single-stage iterative process that allows the exchange of information between the reconstruction and localization. We propose a novel transparency-based diffusion process where the transparency of anomalous regions is progressively increased, restoring their normal appearance accurately while maintaining the appearance of anomaly-free regions using localization cues of previous steps. We implement the proposed process as TRANSparency DifFUSION (TransFusion), a novel discriminative anomaly detection method that achieves state-of-the-art performance on both the VisA and the MVTec AD datasets, with an image-level AUROC of 98.5% and 99.2%, respectively. Code: https://github.com/MaticFuc/ECCV_TransFusion","url_abs":"https://arxiv.org/abs/2311.09999v2","url_pdf":"https://arxiv.org/pdf/2311.09999v2.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":"transfusion-a-transparency-based-diffusion","repo_url":"https://github.com/maticfuc/eccv_transfusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"depth-anomaly-detection-and-segmentation","task_name":"Depth Anomaly Detection and Segmentation"},{"task_slug":"rgb-3d-anomaly-detection-and-segmentation","task_name":"RGB+3D Anomaly Detection and Segmentation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-on-mvtec-ad","task":"Anomaly Detection","dataset":"MVTec AD","model":"TransFusion","rank_in_archive_order":35,"of":148,"metrics":{"Detection AUROC":"99.4","Segmentation AUPRO":"95.3"},"uses_additional_data":true},{"leaderboard":"/sota/anomaly-detection-on-visa","task":"Anomaly Detection","dataset":"VisA","model":"TransFusion","rank_in_archive_order":9,"of":50,"metrics":{"Detection AUROC":"98.7","Segmentation AUPRO (until 30% FPR)":"94.7"},"uses_additional_data":false},{"leaderboard":"/sota/depth-anomaly-detection-and-segmentation-on","task":"Depth Anomaly Detection and Segmentation","dataset":"MVTEC 3D-AD","model":"TransFusion","rank_in_archive_order":1,"of":13,"metrics":{"Detection AUROC":"0.957","Segmentation AUPRO":"0.947"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-3d-anomaly-detection-and-segmentation-on","task":"RGB+3D Anomaly Detection and Segmentation","dataset":"MVTEC 3D-AD","model":"TransFusion","rank_in_archive_order":1,"of":9,"metrics":{"Detection AUCROC":"0.982","Segmentation AUPRO":"0.983"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.09999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09999"}},"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/maticfuc/eccv_transfusion","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"a77eeeca3b6710fd","entry":"gather","repo":"maticfuc/eccv_transfusion","repo_kind":"official","path":"model/TransFusion.py","file_url":"https://github.com/maticfuc/eccv_transfusion/blob/HEAD/model/TransFusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a77eeeca3b6710fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}