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/PointConv

PointConv

Reported on 22 benchmarks across 5 tasks · 1 paper · 4 SOTA

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

Medical8 results

Semantic SegmentationonIntrA
DSC (V)· 2018-11-17
97.18
best: 97.29 (3DMedPT)
SOTA
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
Semantic SegmentationonIntrA
IoU (V)· 2018-11-17
94.65
best: 94.82 (3DMedPT)
SOTA
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
Semantic SegmentationonScanNet
test mIoU· 2018-11-17
55.6
best: 79.8 (PTv3 ARKit LabelMaker)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
Semantic SegmentationonScanNet
val mIoU· 2018-11-17
61
best: 80.5 (DITR)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
Semantic SegmentationonIntrA
DSC (A)· 2018-11-17
86.52
best: 89.71 (3DMedPT)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
Semantic SegmentationonIntrA
IoU (A)· 2018-11-17
79.53
best: 82.39 (3DMedPT)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
Semantic SegmentationonShapeNet-Part
Class Average IoU· 2018-11-17
82.8
best: 87.7 (Feature Geometric Net (FG-Net))
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
Semantic SegmentationonShapeNet-Part
Instance Average IoU· 2018-11-17
85.7
best: 89.1 (GeomGCNN)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246

Audio8 results

10-shot image generationonIntrA
DSC (V)· 2018-11-17
97.18
best: 97.29 (3DMedPT)
SOTA
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
10-shot image generationonIntrA
IoU (V)· 2018-11-17
94.65
best: 94.82 (3DMedPT)
SOTA
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
10-shot image generationonScanNet
test mIoU· 2018-11-17
55.6
best: 79.8 (PTv3 ARKit LabelMaker)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
10-shot image generationonScanNet
val mIoU· 2018-11-17
61
best: 80.5 (DITR)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
10-shot image generationonIntrA
DSC (A)· 2018-11-17
86.52
best: 89.71 (3DMedPT)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
10-shot image generationonIntrA
IoU (A)· 2018-11-17
79.53
best: 82.39 (3DMedPT)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
10-shot image generationonShapeNet-Part
Class Average IoU· 2018-11-17
82.8
best: 87.7 (Feature Geometric Net (FG-Net))
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
10-shot image generationonShapeNet-Part
Instance Average IoU· 2018-11-17
85.7
best: 89.1 (GeomGCNN)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246

Computer Vision6 results

Shape Representation Of 3D Point CloudsonIntrA
F1 score (5-fold)· 2018-11-17
0.883
best: 0.936 (3DMedPT)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· 2018-11-17
92.5
best: 95.3 (PointGST)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
3D Point Cloud ClassificationonIntrA
F1 score (5-fold)· 2018-11-17
0.883
best: 0.936 (3DMedPT)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· 2018-11-17
92.5
best: 95.3 (PointGST)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
3D Point Cloud ReconstructiononIntrA
F1 score (5-fold)· 2018-11-17
0.883
best: 0.936 (3DMedPT)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· 2018-11-17
92.5
best: 95.3 (PointGST)
PointConv: Deep Convolutional Networks on 3D Point Clouds arXiv:1811.07246