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/KPConv

KPConv

Reported on 29 benchmarks across 7 tasks · 2 papers · 20 SOTA

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

Medical13 results

Semantic SegmentationonS3DIS Area5
mAcc· 2019-04-18
72.8
best: 81.6 (Sonata + PTv3)
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
Semantic SegmentationonS3DIS Area5
mIoU· 2019-04-18
67.1
best: 76 (Sonata + PTv3)
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
Semantic SegmentationonS3DIS
mAcc· 2019-04-18
79.1
best: 89.9 (Sonata + PTv3)
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
Semantic SegmentationonDALES
Overall Accuracy· 2019-04-18
97.8
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
Semantic SegmentationonDALES
mIoU· 2019-04-18
81.1
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
Semantic SegmentationonSensatUrban
mIoU· 2019-04-18
57.58
best: 63.4 (LCPFormer)
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
Semantic SegmentationonScanNet
3DIoU· 2019-04-18
68.6
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
Semantic SegmentationonShapeNet-Part
Class Average IoU· 2019-04-18
85.1
best: 87.7 (Feature Geometric Net (FG-Net))
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
Semantic SegmentationonS3DIS
Mean IoU· 2020-12-16
70.6
best: 82.3 (Sonata + PTv3)
Point Transformer arXiv:2012.09164
Semantic SegmentationonS3DIS
Params (M)· 2020-12-16
14.1
best: 41.6 (PointNeXt-XL)
Point Transformer arXiv:2012.09164
Semantic SegmentationonS3DIS
Mean IoU· 2020-12-16
70.6
best: 82.3 (Sonata + PTv3)
Point Transformer arXiv:2012.09164
Semantic SegmentationonS3DIS
Params (M)· 2020-12-16
14.1
best: 41.6 (PointNeXt-XL)
Point Transformer arXiv:2012.09164
Semantic SegmentationonShapeNet-Part
Instance Average IoU· 2019-04-18
86.4
best: 89.1 (GeomGCNN)
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889

Audio13 results

10-shot image generationonS3DIS Area5
mAcc· 2019-04-18
72.8
best: 81.6 (Sonata + PTv3)
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
10-shot image generationonS3DIS Area5
mIoU· 2019-04-18
67.1
best: 76 (Sonata + PTv3)
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
10-shot image generationonS3DIS
mAcc· 2019-04-18
79.1
best: 89.9 (Sonata + PTv3)
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
10-shot image generationonDALES
Overall Accuracy· 2019-04-18
97.8
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
10-shot image generationonDALES
mIoU· 2019-04-18
81.1
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
10-shot image generationonSensatUrban
mIoU· 2019-04-18
57.58
best: 63.4 (LCPFormer)
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
10-shot image generationonScanNet
3DIoU· 2019-04-18
68.6
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
10-shot image generationonShapeNet-Part
Class Average IoU· 2019-04-18
85.1
best: 87.7 (Feature Geometric Net (FG-Net))
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
10-shot image generationonS3DIS
Mean IoU· 2020-12-16
70.6
best: 82.3 (Sonata + PTv3)
Point Transformer arXiv:2012.09164
10-shot image generationonS3DIS
Params (M)· 2020-12-16
14.1
best: 41.6 (PointNeXt-XL)
Point Transformer arXiv:2012.09164
10-shot image generationonS3DIS
Mean IoU· 2020-12-16
70.6
best: 82.3 (Sonata + PTv3)
Point Transformer arXiv:2012.09164
10-shot image generationonS3DIS
Params (M)· 2020-12-16
14.1
best: 41.6 (PointNeXt-XL)
Point Transformer arXiv:2012.09164
10-shot image generationonShapeNet-Part
Instance Average IoU· 2019-04-18
86.4
best: 89.1 (GeomGCNN)
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889

Computer Vision7 results

3D Semantic SegmentationonDALES
Overall Accuracy· 2019-04-18
97.8
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
3D Semantic SegmentationonDALES
mIoU· 2019-04-18
81.1
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
3D Semantic SegmentationonSensatUrban
mIoU· 2019-04-18
57.58
best: 63.4 (LCPFormer)
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
Scene SegmentationonScanNet
3DIoU· 2019-04-18
68.6
SOTA
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· 2019-04-18
92.9
best: 95.3 (PointGST)
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· 2019-04-18
92.9
best: 95.3 (PointGST)
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· 2019-04-18
92.9
best: 95.3 (PointGST)
KPConv: Flexible and Deformable Convolution for Point Clouds arXiv:1904.08889