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/SPoTr

SPoTr

Reported on 25 benchmarks across 5 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 Vision15 results

Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy (PB_T50_RS)· 2023-03-29
88.6
best: 92.64 (Mamba3D)
SOTA
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy (PB_T50_RS)· 2023-03-29
88.6
best: 92.64 (Mamba3D)
SOTA
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy (PB_T50_RS)· 2023-03-29
88.6
best: 92.64 (Mamba3D)
SOTA
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
Shape Representation Of 3D Point CloudsonScanObjectNN
Mean Accuracy· 2023-03-29
86.8
best: 93.8 (GPSFormer)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· 2023-03-29
88.6
best: 97.2 (OmniVec2)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
Shape Representation Of 3D Point CloudsonScanObjectNN
GFLOPs· 2023-03-29
10.8
best: 45 (PCM)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
Shape Representation Of 3D Point CloudsonScanObjectNN
Number of params (M)· 2023-03-29
1.7
best: 34.2 (PCM)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
3D Point Cloud ClassificationonScanObjectNN
Mean Accuracy· 2023-03-29
86.8
best: 93.8 (GPSFormer)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· 2023-03-29
88.6
best: 97.2 (OmniVec2)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
3D Point Cloud ClassificationonScanObjectNN
GFLOPs· 2023-03-29
10.8
best: 45 (PCM)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
3D Point Cloud ClassificationonScanObjectNN
Number of params (M)· 2023-03-29
1.7
best: 34.2 (PCM)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
3D Point Cloud ReconstructiononScanObjectNN
Mean Accuracy· 2023-03-29
86.8
best: 93.8 (GPSFormer)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· 2023-03-29
88.6
best: 97.2 (OmniVec2)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
3D Point Cloud ReconstructiononScanObjectNN
GFLOPs· 2023-03-29
10.8
best: 45 (PCM)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
3D Point Cloud ReconstructiononScanObjectNN
Number of params (M)· 2023-03-29
1.7
best: 34.2 (PCM)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450

Medical5 results

Semantic SegmentationonS3DIS Area5
mAcc· 2023-03-29
76.4
best: 81.6 (Sonata + PTv3)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
Semantic SegmentationonS3DIS Area5
mIoU· 2023-03-29
70.8
best: 76 (Sonata + PTv3)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
Semantic SegmentationonS3DIS Area5
oAcc· 2023-03-29
90.7
best: 93 (Sonata + PTv3)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
Semantic SegmentationonShapeNet-Part
Class Average IoU· 2023-03-29
85.4
best: 87.7 (Feature Geometric Net (FG-Net))
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
Semantic SegmentationonShapeNet-Part
Instance Average IoU· 2023-03-29
87.2
best: 89.1 (GeomGCNN)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450

Audio5 results

10-shot image generationonS3DIS Area5
mAcc· 2023-03-29
76.4
best: 81.6 (Sonata + PTv3)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
10-shot image generationonS3DIS Area5
mIoU· 2023-03-29
70.8
best: 76 (Sonata + PTv3)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
10-shot image generationonS3DIS Area5
oAcc· 2023-03-29
90.7
best: 93 (Sonata + PTv3)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
10-shot image generationonShapeNet-Part
Class Average IoU· 2023-03-29
85.4
best: 87.7 (Feature Geometric Net (FG-Net))
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450
10-shot image generationonShapeNet-Part
Instance Average IoU· 2023-03-29
87.2
best: 89.1 (GeomGCNN)
Self-positioning Point-based Transformer for Point Cloud Understanding arXiv:2303.16450