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/PointNeXt-XL

PointNeXt-XL

Reported on 14 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.

Medical6 results

Semantic SegmentationonS3DIS
Params (M)· 2022-06-09
41.6
SOTA
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670
Semantic SegmentationonS3DIS
Mean IoU· 2022-06-09
74.9
best: 82.3 (Sonata + PTv3)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670
Semantic SegmentationonS3DIS
mAcc· 2022-06-09
83
best: 89.9 (Sonata + PTv3)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670
Semantic SegmentationonS3DIS
oAcc· 2022-06-09
90.3
best: 93.3 (Sonata + PTv3)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670
Semantic SegmentationonOpenTrench3D
mAcc· 2022-06-09
79.7
best: 84.5 (PointMetaBase-XXL)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670
Semantic SegmentationonOpenTrench3D
mIoU· 2022-06-09
70.6
best: 76.5 (PointVector-XL)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670

Audio6 results

10-shot image generationonS3DIS
Params (M)· 2022-06-09
41.6
SOTA
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670
10-shot image generationonS3DIS
Mean IoU· 2022-06-09
74.9
best: 82.3 (Sonata + PTv3)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670
10-shot image generationonS3DIS
mAcc· 2022-06-09
83
best: 89.9 (Sonata + PTv3)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670
10-shot image generationonS3DIS
oAcc· 2022-06-09
90.3
best: 93.3 (Sonata + PTv3)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670
10-shot image generationonOpenTrench3D
mAcc· 2022-06-09
79.7
best: 84.5 (PointMetaBase-XXL)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670
10-shot image generationonOpenTrench3D
mIoU· 2022-06-09
70.6
best: 76.5 (PointVector-XL)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670

Computer Vision2 results

3D Semantic SegmentationonOpenTrench3D
mAcc· 2022-06-09
79.7
best: 84.5 (PointMetaBase-XXL)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670
3D Semantic SegmentationonOpenTrench3D
mIoU· 2022-06-09
70.6
best: 76.5 (PointVector-XL)
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies arXiv:2206.04670