TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/GeoTransformer

GeoTransformer

Reported on 74 benchmarks across 2 tasks · 2 papers · 40 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision74 results

  • Point Cloud RegistrationonFP-R-E
    RRE (degrees)· 2023-07-25
    2.29
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-R-E
    RTE (cm)· 2023-07-25
    1.57
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-R-H
    RTE (cm)· 2023-07-25
    1.69
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-O-M
    RRE (degrees)· 2023-07-25
    2.45
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-O-M
    RTE (cm)· 2023-07-25
    1.94
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-O-E
    RRE (degrees)· 2023-07-25
    2.3
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-O-E
    RTE (cm)· 2023-07-25
    1.57
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-T-M
    RRE (degrees)· 2023-07-25
    2.29
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-T-M
    RTE (cm)· 2023-07-25
    1.58
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-T-E
    RRE (degrees)· 2023-07-25
    2.32
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-T-E
    RTE (cm)· 2023-07-25
    1.59
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-R-M
    RRE (degrees)· 2023-07-25
    2.26
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-T-H
    RRE (degrees)· 2023-07-25
    2.27
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-T-H
    RTE (cm)· 2023-07-25
    1.57
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonRotKITTI Registration Benchmark
    RR@(1,0.1)· 2023-07-25
    50.1
    best: 73.3 (UMERegRobust)
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonRotKITTI Registration Benchmark
    RR@(1.5,0.3)· 2023-07-25
    78.5
    best: 81.1 (UMERegRobust)
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-O-H
    RRE (degrees)· 2023-07-25
    2.57
    best: 2.68 (FCGF+SC2-PCR)
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-O-H
    RTE (cm)· 2023-07-25
    2.22
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-R-E
    RRE (degrees)· 2023-07-25
    2.29
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-R-E
    RTE (cm)· 2023-07-25
    1.57
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-R-H
    RTE (cm)· 2023-07-25
    1.69
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-O-M
    RRE (degrees)· 2023-07-25
    2.45
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-O-M
    RTE (cm)· 2023-07-25
    1.94
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-O-E
    RRE (degrees)· 2023-07-25
    2.3
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-O-E
    RTE (cm)· 2023-07-25
    1.57
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-T-M
    RRE (degrees)· 2023-07-25
    2.29
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-T-M
    RTE (cm)· 2023-07-25
    1.58
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-T-E
    RRE (degrees)· 2023-07-25
    2.32
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-T-E
    RTE (cm)· 2023-07-25
    1.59
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-R-M
    RRE (degrees)· 2023-07-25
    2.26
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-T-H
    RRE (degrees)· 2023-07-25
    2.27
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-T-H
    RTE (cm)· 2023-07-25
    1.57
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonRotKITTI Registration Benchmark
    RR@(1,0.1)· 2023-07-25
    50.1
    best: 73.3 (UMERegRobust)
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonRotKITTI Registration Benchmark
    RR@(1.5,0.3)· 2023-07-25
    78.5
    best: 81.1 (UMERegRobust)
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-O-H
    RRE (degrees)· 2023-07-25
    2.57
    best: 2.68 (FCGF+SC2-PCR)
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-O-H
    RTE (cm)· 2023-07-25
    2.22
    SOTA
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonKITTI (FCGF setting)
    Recall (0.6m, 5 degrees)· 2022-02-14
    99.5
    SOTA
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688
  • Point Cloud RegistrationonFPv1
    Recall (3cm, 10 degrees)· 2022-02-14
    56.15
    best: 92.81 (Greedy Grid Search)
    SOTA
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688
  • 3D Point Cloud InterpolationonKITTI (FCGF setting)
    Recall (0.6m, 5 degrees)· 2022-02-14
    99.5
    SOTA
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688
  • 3D Point Cloud InterpolationonFPv1
    Recall (3cm, 10 degrees)· 2022-02-14
    56.15
    best: 92.81 (Greedy Grid Search)
    SOTA
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688
  • Point Cloud RegistrationonFP-R-E
    Recall (3cm, 10 degrees)· 2023-07-25
    64.12
    best: 99.76 (GeDi)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-R-H
    RRE (degrees)· 2023-07-25
    0.47
    best: 1.77 (FCGF+SC2-PCR )
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-R-H
    Recall (3cm, 10 degrees)· 2023-07-25
    47.75
    best: 99.41 (GeDi)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonKITTI (trained on 3DMatch)
    Success Rate· 2023-07-25
    67.93
    best: 98.92 (GeDi)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-O-M
    Recall (3cm, 10 degrees)· 2023-07-25
    22.07
    best: 88.06 (Exhaustive Grid Search)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-O-E
    Recall (3cm, 10 degrees)· 2023-07-25
    63.94
    best: 99.88 (FPFH+SC2-PCR )
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonETH (trained on 3DMatch)
    Recall (30cm, 5 degrees)· 2023-07-25
    4.91
    best: 94.25 (Exhaustive Grid Search)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-T-M
    Recall (3cm, 10 degrees)· 2023-07-25
    64.29
    best: 99.82 (Exhaustive Grid Search)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-T-E
    Recall (3cm, 10 degrees)· 2023-07-25
    66.25
    best: 99.76 (FPFH+SC2-PCR)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-R-M
    RTE (cm)· 2023-07-25
    1.63
    best: 2.71 (GO-ICP)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-R-M
    Recall (3cm, 10 degrees)· 2023-07-25
    55.93
    best: 99.94 (GeDi)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-T-H
    Recall (3cm, 10 degrees)· 2023-07-25
    64.18
    best: 99.7 (GeDi)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud RegistrationonFP-O-H
    Recall (3cm, 10 degrees)· 2023-07-25
    2.64
    best: 38.85 (FPFH+SC2-PCR)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-R-E
    Recall (3cm, 10 degrees)· 2023-07-25
    64.12
    best: 99.76 (GeDi)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-R-H
    RRE (degrees)· 2023-07-25
    0.47
    best: 1.77 (FCGF+SC2-PCR )
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-R-H
    Recall (3cm, 10 degrees)· 2023-07-25
    47.75
    best: 99.41 (GeDi)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonKITTI (trained on 3DMatch)
    Success Rate· 2023-07-25
    67.93
    best: 98.92 (GeDi)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-O-M
    Recall (3cm, 10 degrees)· 2023-07-25
    22.07
    best: 88.06 (Exhaustive Grid Search)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-O-E
    Recall (3cm, 10 degrees)· 2023-07-25
    63.94
    best: 99.88 (FPFH+SC2-PCR )
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonETH (trained on 3DMatch)
    Recall (30cm, 5 degrees)· 2023-07-25
    4.91
    best: 94.25 (Exhaustive Grid Search)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-T-M
    Recall (3cm, 10 degrees)· 2023-07-25
    64.29
    best: 99.82 (Exhaustive Grid Search)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-T-E
    Recall (3cm, 10 degrees)· 2023-07-25
    66.25
    best: 99.76 (FPFH+SC2-PCR)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-R-M
    RTE (cm)· 2023-07-25
    1.63
    best: 2.71 (GO-ICP)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-R-M
    Recall (3cm, 10 degrees)· 2023-07-25
    55.93
    best: 99.94 (GeDi)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-T-H
    Recall (3cm, 10 degrees)· 2023-07-25
    64.18
    best: 99.7 (GeDi)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • 3D Point Cloud InterpolationonFP-O-H
    Recall (3cm, 10 degrees)· 2023-07-25
    2.64
    best: 38.85 (FPFH+SC2-PCR)
    GeoTransformer: Fast and Robust Point Cloud Registration with Geometric TransformerarXiv:2308.03768
  • Point Cloud Registrationon3DMatch (at least 30% overlapped - FCGF setting)
    Recall (0.3m, 15 degrees)· 2022-02-14
    95
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688
  • Point Cloud RegistrationonScanNet++ (trained on 3DMatch)
    Recall ( correspondence RMSE below 0.2)· 2022-02-14
    73.4
    best: 63.7 (Predator)
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688
  • Point Cloud RegistrationonFPv1
    RRE (degrees)· 2022-02-14
    2.423
    best: 4.489 (FCGF + YOHO-O)
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688
  • Point Cloud RegistrationonFPv1
    RTE (cm)· 2022-02-14
    1.581
    best: 2.052 (DIP)
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688
  • 3D Point Cloud Interpolationon3DMatch (at least 30% overlapped - FCGF setting)
    Recall (0.3m, 15 degrees)· 2022-02-14
    95
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688
  • 3D Point Cloud InterpolationonScanNet++ (trained on 3DMatch)
    Recall ( correspondence RMSE below 0.2)· 2022-02-14
    73.4
    best: 63.7 (Predator)
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688
  • 3D Point Cloud InterpolationonFPv1
    RRE (degrees)· 2022-02-14
    2.423
    best: 4.489 (FCGF + YOHO-O)
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688
  • 3D Point Cloud InterpolationonFPv1
    RTE (cm)· 2022-02-14
    1.581
    best: 2.052 (DIP)
    Geometric Transformer for Fast and Robust Point Cloud RegistrationarXiv:2202.06688