GPSFormer

Reported on 6 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Computer Vision6 results

Shape Representation Of 3D Point CloudsonScanObjectNN
Mean Accuracy· 2024-07-18
93.8
SOTA
GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding arXiv:2407.13519
3D Point Cloud ClassificationonScanObjectNN
Mean Accuracy· 2024-07-18
93.8
SOTA
GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding arXiv:2407.13519
3D Point Cloud ReconstructiononScanObjectNN
Mean Accuracy· 2024-07-18
93.8
SOTA
GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding arXiv:2407.13519
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· 2024-07-18
95.4
best: 97.2 (OmniVec2)
GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding arXiv:2407.13519
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· 2024-07-18
95.4
best: 97.2 (OmniVec2)
GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding arXiv:2407.13519
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· 2024-07-18
95.4
best: 97.2 (OmniVec2)
GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding arXiv:2407.13519