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/GeomGCNN

GeomGCNN

Reported on 7 benchmarks across 3 tasks · 1 paper · 2 SOTA

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

Medical3 results

Semantic SegmentationonShapeNet-Part
Instance Average IoU· 2021-03-28
89.1
SOTA
Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks arXiv:2103.15226
Semantic SegmentationonS3DIS Area5
mIoU· 2021-03-28
69.4
best: 76 (Sonata + PTv3)
Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks arXiv:2103.15226
Semantic SegmentationonS3DIS Area5
oAcc· 2021-03-28
89.4
best: 93 (Sonata + PTv3)
Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks arXiv:2103.15226

Audio3 results

10-shot image generationonShapeNet-Part
Instance Average IoU· 2021-03-28
89.1
SOTA
Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks arXiv:2103.15226
10-shot image generationonS3DIS Area5
mIoU· 2021-03-28
69.4
best: 76 (Sonata + PTv3)
Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks arXiv:2103.15226
10-shot image generationonS3DIS Area5
oAcc· 2021-03-28
89.4
best: 93 (Sonata + PTv3)
Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks arXiv:2103.15226

Computer Vision1 result

LIDAR Semantic SegmentationonParis-Lille-3D
mIOU· 2021-03-28
0.785
best: 0.827 (FKAConv)
Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks arXiv:2103.15226