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+TAP

PointMLP+TAP

Reported on 7 benchmarks across 5 tasks · 1 paper

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

Computer Vision3 results

Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· 2023-07-27
88.5
best: 97.2 (OmniVec2)
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models arXiv:2307.14971
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· 2023-07-27
88.5
best: 97.2 (OmniVec2)
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models arXiv:2307.14971
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· 2023-07-27
88.5
best: 97.2 (OmniVec2)
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models arXiv:2307.14971

Medical2 results

Semantic SegmentationonShapeNet-Part
Class Average IoU· 2023-07-27
85.2
best: 87.7 (Feature Geometric Net (FG-Net))
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models arXiv:2307.14971
Semantic SegmentationonShapeNet-Part
Instance Average IoU· 2023-07-27
86.9
best: 89.1 (GeomGCNN)
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models arXiv:2307.14971

Audio2 results

10-shot image generationonShapeNet-Part
Class Average IoU· 2023-07-27
85.2
best: 87.7 (Feature Geometric Net (FG-Net))
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models arXiv:2307.14971
10-shot image generationonShapeNet-Part
Instance Average IoU· 2023-07-27
86.9
best: 89.1 (GeomGCNN)
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models arXiv:2307.14971