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/PAConv

PAConv

Reported on 8 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 Vision7 results

Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· 2021-03-26
93.9
best: 95.3 (PointGST)
SOTA
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds arXiv:2103.14635
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· 2021-03-26
93.9
best: 95.3 (PointGST)
SOTA
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds arXiv:2103.14635
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· 2021-03-26
93.9
best: 95.3 (PointGST)
SOTA
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds arXiv:2103.14635
Shape Representation Of 3D Point CloudsonIntrA
F1 score (5-fold)· 2021-03-26
0.906
best: 0.936 (3DMedPT)
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds arXiv:2103.14635
3D Point Cloud ClassificationonIntrA
F1 score (5-fold)· 2021-03-26
0.906
best: 0.936 (3DMedPT)
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds arXiv:2103.14635
Point Cloud SegmentationonPointCloud-C
mean Corruption Error (mCE)· 2021-03-26
0.927
best: 0.923 (GDANet)
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds arXiv:2103.14635
3D Point Cloud ReconstructiononIntrA
F1 score (5-fold)· 2021-03-26
0.906
best: 0.936 (3DMedPT)
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds arXiv:2103.14635

Graphs1 result

Point Cloud ClassificationonPointCloud-C
mean Corruption Error (mCE)· 2021-03-26
1.104
best: 0.455 (BeyondRPC)
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds arXiv:2103.14635