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/PPT + SparseUNet

PPT + SparseUNet

Reported on 16 benchmarks across 2 tasks · 1 paper

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

Medical8 results

Semantic SegmentationonScanNet
test mIoU· uses extra data· 2023-08-18
76.6
best: 79.8 (PTv3 ARKit LabelMaker)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
Semantic SegmentationonScanNet
val mIoU· uses extra data· 2023-08-18
76.4
best: 80.5 (DITR)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
Semantic SegmentationonS3DIS Area5
mAcc· uses extra data· 2023-08-18
78.2
best: 81.6 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
Semantic SegmentationonS3DIS Area5
mIoU· uses extra data· 2023-08-18
72.7
best: 76 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
Semantic SegmentationonS3DIS Area5
oAcc· uses extra data· 2023-08-18
91.5
best: 93 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
Semantic SegmentationonS3DIS
Mean IoU· uses extra data· 2023-08-18
78.1
best: 82.3 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
Semantic SegmentationonS3DIS
mAcc· uses extra data· 2023-08-18
85.4
best: 89.9 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
Semantic SegmentationonS3DIS
oAcc· uses extra data· 2023-08-18
92.2
best: 93.3 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718

Audio8 results

10-shot image generationonScanNet
test mIoU· uses extra data· 2023-08-18
76.6
best: 79.8 (PTv3 ARKit LabelMaker)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
10-shot image generationonScanNet
val mIoU· uses extra data· 2023-08-18
76.4
best: 80.5 (DITR)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
10-shot image generationonS3DIS Area5
mAcc· uses extra data· 2023-08-18
78.2
best: 81.6 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
10-shot image generationonS3DIS Area5
mIoU· uses extra data· 2023-08-18
72.7
best: 76 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
10-shot image generationonS3DIS Area5
oAcc· uses extra data· 2023-08-18
91.5
best: 93 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
10-shot image generationonS3DIS
Mean IoU· uses extra data· 2023-08-18
78.1
best: 82.3 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
10-shot image generationonS3DIS
mAcc· uses extra data· 2023-08-18
85.4
best: 89.9 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718
10-shot image generationonS3DIS
oAcc· uses extra data· 2023-08-18
92.2
best: 93.3 (Sonata + PTv3)
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training arXiv:2308.09718