{"url":"/dataset/3dmatch","name":"3DMatch","full_name":null,"description_markdown":"The 3DMATCH benchmark evaluates how well descriptors (both 2D and 3D) can establish correspondences between RGB-D frames of different views. The dataset contains 2D RGB-D patches and 3D patches (local TDF voxel grid volumes) of wide-baselined correspondences. \r\n\r\nThe pixel size of each 2D patch is determined by the projection of the 0.3m3 local 3D patch around the interest point onto the image plane. \r\n\r\nSource: [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](/paper/3dmatch-learning-local-geometric-descriptors)","description_withheld":null,"homepage":"http://3dmatch.cs.princeton.edu/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/3dmatch-learning-local-geometric-descriptors","title":"3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions","first_author":"Andy Zeng","url":null},"license":{"name":"Various","url":"https://3dmatch.cs.princeton.edu/"},"modalities":[],"tasks":[{"name":"Point Cloud Registration","url":"/task/point-cloud-registration","datasets_with_task":"/datasets/task/point-cloud-registration"},{"name":"Low-Light Image Enhancement","url":"/task/low-light-image-enhancement","datasets_with_task":"/datasets/task/low-light-image-enhancement"},{"name":"3D Feature Matching","url":"/task/3d-feature-matching","datasets_with_task":"/datasets/task/3d-feature-matching"}],"languages":[],"variants":["3DMatch Benchmark","3DMatch"],"data_loaders":[],"num_papers_in_archive":175,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/point-cloud-registration-on-3dmatch-benchmark","task":"Point Cloud Registration","dataset_variant":"3DMatch Benchmark","rows":15,"metrics":["Feature Matching Recall"],"first_row_in_archive_order":{"model":"IMFNet","paper":"/paper/imfnet-interpretable-multimodal-fusion-for","metrics":{"Feature Matching Recall":"98.6"},"code_links":[{"title":"XiaoshuiHuang/IMFNet","url":"https://github.com/XiaoshuiHuang/IMFNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-feature-matching-on-3dmatch-benchmark","task":"3D Feature Matching","dataset_variant":"3DMatch Benchmark","rows":1,"metrics":["Average Recall"],"first_row_in_archive_order":{"model":"FCGF","paper":"/paper/fully-convolutional-geometric-features","metrics":{"Average Recall":"0.9578"},"code_links":[{"title":"chrischoy/FCGF","url":"https://github.com/chrischoy/FCGF"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/low-light-image-enhancement-on-3dmatch","task":"Low-Light Image Enhancement","dataset_variant":"3DMatch Benchmark","rows":1,"metrics":["mAP (@0.1, Through-wall)"],"first_row_in_archive_order":{"model":"nnh","paper":"/paper/attention-guided-low-light-image-enhancement","metrics":{"mAP (@0.1, Through-wall)":"224"},"code_links":[{"title":"Lvfeifan/MBLLEN","url":"https://github.com/Lvfeifan/MBLLEN"},{"title":"yu-li/AGLLNet","url":"https://github.com/yu-li/AGLLNet"},{"title":"bchao1/awesome-image-enhancement","url":"https://github.com/bchao1/awesome-image-enhancement"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/points-to-patches-enabling-the-use-of-self","title":"Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition","date":"2022-04-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/imfnet-interpretable-multimodal-fusion-for","title":"IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration","date":"2021-11-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/generalisable-and-distinctive-3d-local-deep","title":"Learning general and distinctive 3D local deep descriptors for point cloud registration","date":"2021-05-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/3d-point-cloud-registration-with-multi-scale","title":"3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning","date":"2021-03-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spinnet-learning-a-general-surface-descriptor","title":"SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration","date":"2020-11-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/distinctive-3d-local-deep-descriptors","title":"Distinctive 3D local deep descriptors","date":"2020-09-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/end-to-end-learning-local-multi-view","title":"End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds","date":"2020-03-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":1,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/d3feat-joint-learning-of-dense-detection-and","title":"D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features","date":"2020-03-06","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fully-convolutional-geometric-features","title":"Fully Convolutional Geometric Features","date":"2019-10-27","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/attention-guided-low-light-image-enhancement","title":"Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset","date":"2019-08-02","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/the-perfect-match-3d-point-cloud-matching","title":"The Perfect Match: 3D Point Cloud Matching with Smoothed Densities","date":"2018-11-16","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ppf-foldnet-unsupervised-learning-of-rotation","title":"PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors","date":"2018-08-30","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ppfnet-global-context-aware-local-features","title":"PPFNet: Global Context Aware Local Features for Robust 3D Point Matching","date":"2018-02-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/3dmatch-learning-local-geometric-descriptors","title":"3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions","date":"2016-03-27","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/fast-point-feature-histograms-fpfh-for-3d","title":"Fast Point Feature Histograms (FPFH) for 3D Registration","date":"2009-05-12","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":32,"samples_ran":3,"samples_unverified":29,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}