{"url":"/sota/3d-dense-shape-correspondence-on-shrec-19","task":{"name":"3D Dense Shape Correspondence","url":"/task/3d-dense-shape-correspondence","note":null},"dataset":{"name":"SHREC'19","url":"/dataset/shrec-19"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Finding a meaningful correspondence between two or more shapes is one of the most fundamental shape analysis tasks. The problem can be generally stated as: given input shapes S1,S2,...,SN, find a meaningful relation (or mapping) between their elements. Under different contexts, the problem has also been referred to as registration, alignment, or simply, matching. Shape correspondence is a key algorithmic component in tasks such as 3D scan alignment and space-time reconstruction, as well as an indispensable prerequisite in diverse applications including attribute transfer, shape interpolation, and statistical modeling.","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":["Euclidean Mean Error (EME)","Accuracy at 1%"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Euclidean Mean Error (EME)":"lower","Accuracy at 1%":"higher"}},"counts":{"rows":11,"rows_with_code":10,"rows_with_paper_page":11,"rows_dated":11,"rows_using_additional_data":7},"rows":[{"rank_in_archive_order":1,"model":"Diffusion 3D Features (Zero-shot)","metrics":{"Accuracy at 1%":"26.4","Euclidean Mean Error (EME)":"1.7"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/diffusion-3d-features-diff3f-decorating","paper_url":"https://arxiv.org/abs/2311.17024v2","paper_title":"Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features","code":"https://github.com/niladridutt/Diffusion-3D-Features","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"TANet (Trained on Surreal)","metrics":{"Accuracy at 1%":"21.5","Euclidean Mean Error (EME)":"4.5"},"uses_additional_data":true,"paper_date":"2024-03-25","paper":"/paper/unsupervised-template-assisted-point-cloud","paper_url":"https://arxiv.org/abs/2403.16412v1","paper_title":"Unsupervised Template-assisted Point Cloud Shape Correspondence Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"SE-ORNet (Trained on Surreal)","metrics":{"Accuracy at 1%":"21.5","Euclidean Mean Error (EME)":"4.6"},"uses_additional_data":true,"paper_date":"2023-04-10","paper":"/paper/se-ornet-self-ensembling-orientation-aware","paper_url":"https://arxiv.org/abs/2304.05395v1","paper_title":"SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence","code":"https://github.com/openspaceai/se-ornet","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"SE-ORNet","metrics":{"Accuracy at 1%":"17.5","Euclidean Mean Error (EME)":"5.1"},"uses_additional_data":false,"paper_date":"2023-04-10","paper":"/paper/se-ornet-self-ensembling-orientation-aware","paper_url":"https://arxiv.org/abs/2304.05395v1","paper_title":"SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence","code":"https://github.com/openspaceai/se-ornet","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"DPC","metrics":{"Accuracy at 1%":"15.3","Euclidean Mean Error (EME)":"5.6"},"uses_additional_data":false,"paper_date":"2021-10-16","paper":"/paper/dpc-unsupervised-deep-point-correspondence","paper_url":"https://arxiv.org/abs/2110.08636v1","paper_title":"DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction","code":"https://github.com/dvirginz/dpc","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DPC (Trained on Surreal)","metrics":{"Accuracy at 1%":"17.7","Euclidean Mean Error (EME)":"6.1"},"uses_additional_data":true,"paper_date":"2021-10-16","paper":"/paper/dpc-unsupervised-deep-point-correspondence","paper_url":"https://arxiv.org/abs/2110.08636v1","paper_title":"DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction","code":"https://github.com/dvirginz/dpc","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"CorrNet3D (Trained on Surreal)","metrics":{"Accuracy at 1%":"6.0","Euclidean Mean Error (EME)":"6.9"},"uses_additional_data":true,"paper_date":"2020-12-31","paper":"/paper/corrnet3d-unsupervised-end-to-end-learning-of","paper_url":"https://arxiv.org/abs/2012.15638v2","paper_title":"CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds","code":"https://github.com/ZENGYIMING-EAMON/CorrNet3D","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"Diff-FMaps  (Trained on Surreal)","metrics":{"Accuracy at 1%":"4.0","Euclidean Mean Error (EME)":"7.1"},"uses_additional_data":true,"paper_date":"2020-10-25","paper":"/paper/correspondence-learning-via-linearly","paper_url":"https://arxiv.org/abs/2010.13136v1","paper_title":"Correspondence Learning via Linearly-invariant Embedding","code":"https://github.com/riccardomarin/diff-fmaps-pytorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"Elementery  Structures(Trained on Surreal)","metrics":{"Accuracy at 1%":"2.3","Euclidean Mean Error (EME)":"7.6"},"uses_additional_data":true,"paper_date":"2019-08-13","paper":"/paper/learning-elementary-structures-for-3d-shape","paper_url":"https://arxiv.org/abs/1908.04725v2","paper_title":"Learning elementary structures for 3D shape generation and matching","code":"https://github.com/ThibaultGROUEIX/3D-CODED","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"3DCODED (Trained on Surreal)","metrics":{"Accuracy at 1%":"2.1","Euclidean Mean Error (EME)":"8.1"},"uses_additional_data":true,"paper_date":"2018-06-13","paper":"/paper/3d-coded-3d-correspondences-by-deep-1","paper_url":"http://arxiv.org/abs/1806.05228v2","paper_title":"3D-CODED : 3D Correspondences by Deep Deformation","code":"https://github.com/ThibaultGROUEIX/3D-CODED","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"CorrNet3D","metrics":{"Accuracy at 1%":"0.4","Euclidean Mean Error (EME)":"33.8"},"uses_additional_data":false,"paper_date":"2020-12-31","paper":"/paper/corrnet3d-unsupervised-end-to-end-learning-of","paper_url":"https://arxiv.org/abs/2012.15638v2","paper_title":"CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds","code":"https://github.com/ZENGYIMING-EAMON/CorrNet3D","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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"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"}}}