Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/PointMLP

PointMLP

Reported on 22 benchmarks across 4 tasks · 1 paper · 15 SOTA

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

Computer Vision22 results

Shape Representation Of 3D Point CloudsonScanObjectNN
Mean Accuracy· 2022-02-15
84.4
best: 93.8 (GPSFormer)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· 2022-02-15
85.7
best: 97.2 (OmniVec2)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· 2022-02-15
94.5
best: 95.3 (PointGST)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
Shape Representation Of 3D Point CloudsonScanObjectNN
GFLOPs· 2022-02-15
31.4
best: 45 (PCM)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy (PB_T50_RS)· 2022-02-15
85.4
best: 92.64 (Mamba3D)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ClassificationonScanObjectNN
Mean Accuracy· 2022-02-15
84.4
best: 93.8 (GPSFormer)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· 2022-02-15
85.7
best: 97.2 (OmniVec2)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· 2022-02-15
94.5
best: 95.3 (PointGST)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ClassificationonScanObjectNN
GFLOPs· 2022-02-15
31.4
best: 45 (PCM)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy (PB_T50_RS)· 2022-02-15
85.4
best: 92.64 (Mamba3D)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ReconstructiononScanObjectNN
Mean Accuracy· 2022-02-15
84.4
best: 93.8 (GPSFormer)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· 2022-02-15
85.7
best: 97.2 (OmniVec2)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· 2022-02-15
94.5
best: 95.3 (PointGST)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ReconstructiononScanObjectNN
GFLOPs· 2022-02-15
31.4
best: 45 (PCM)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy (PB_T50_RS)· 2022-02-15
85.4
best: 92.64 (Mamba3D)
SOTA
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
Shape Representation Of 3D Point CloudsonModelNet40
Mean Accuracy· 2022-02-15
91.4
best: 92.4 (ULIP + PointMLP)
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
Shape Representation Of 3D Point CloudsonScanObjectNN
Number of params (M)· 2022-02-15
12.6
best: 34.2 (PCM)
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ClassificationonModelNet40
Mean Accuracy· 2022-02-15
91.4
best: 92.4 (ULIP + PointMLP)
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ClassificationonScanObjectNN
Number of params (M)· 2022-02-15
12.6
best: 34.2 (PCM)
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
Point Cloud SegmentationonPointCloud-C
mean Corruption Error (mCE)· 2022-02-15
0.977
best: 0.923 (GDANet)
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ReconstructiononModelNet40
Mean Accuracy· 2022-02-15
91.4
best: 92.4 (ULIP + PointMLP)
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123
3D Point Cloud ReconstructiononScanObjectNN
Number of params (M)· 2022-02-15
12.6
best: 34.2 (PCM)
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework arXiv:2202.07123