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/PointNet++

PointNet++

Reported on 96 benchmarks across 7 tasks · 2 papers · 59 SOTA

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

Computer Vision62 results

Shape Representation Of 3D Point CloudsonScanObjectNN
Mean Accuracy· 2017-06-07
75.4
best: 93.8 (GPSFormer)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-BG (OA)· 2017-06-07
82.3
best: 99.48 (PointGST)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-ONLY (OA)· 2017-06-07
84.3
best: 97.76 (PointGST)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· 2017-06-07
77.9
best: 97.2 (OmniVec2)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonIntrA
F1 score (5-fold)· 2017-06-07
0.903
best: 0.936 (3DMedPT)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonModelNet40-C
Error Rate· 2017-06-07
0.236
best: 0.142 (OmniVec2)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Standard Deviation· 2017-06-07
16
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonScanObjectNN
GFLOPs· 2017-06-07
1.7
best: 45 (PCM)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy (PB_T50_RS)· 2017-06-07
77.9
best: 92.64 (Mamba3D)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Semantic SegmentationonDALES
Overall Accuracy· 2017-06-07
95.7
best: 97.8 (KPConv)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Semantic SegmentationonDALES
mIoU· 2017-06-07
68.3
best: 81.1 (KPConv)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Semantic SegmentationonSTPLS3D
mIOU· 2017-06-07
15.92
best: 53.73 (KpConv)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Semantic SegmentationonKITTI-360
mIoU Category· 2017-06-07
58.28
best: 74.08 (MinkowskiNet)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Semantic SegmentationonKITTI-360
miou· 2017-06-07
35.66
best: 58.3 (DeepViewAgg)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonScanObjectNN
Mean Accuracy· 2017-06-07
75.4
best: 93.8 (GPSFormer)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonScanObjectNN
OBJ-BG (OA)· 2017-06-07
82.3
best: 99.48 (PointGST)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonScanObjectNN
OBJ-ONLY (OA)· 2017-06-07
84.3
best: 97.76 (PointGST)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· 2017-06-07
77.9
best: 97.2 (OmniVec2)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonIntrA
F1 score (5-fold)· 2017-06-07
0.903
best: 0.936 (3DMedPT)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonModelNet40-C
Error Rate· 2017-06-07
0.236
best: 0.142 (OmniVec2)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Standard Deviation· 2017-06-07
16
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonScanObjectNN
GFLOPs· 2017-06-07
1.7
best: 45 (PCM)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy (PB_T50_RS)· 2017-06-07
77.9
best: 92.64 (Mamba3D)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Point Cloud SegmentationonPointCloud-C
mean Corruption Error (mCE)· 2017-06-07
1.112
best: 0.923 (GDANet)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononScanObjectNN
Mean Accuracy· 2017-06-07
75.4
best: 93.8 (GPSFormer)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononScanObjectNN
OBJ-BG (OA)· 2017-06-07
82.3
best: 99.48 (PointGST)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononScanObjectNN
OBJ-ONLY (OA)· 2017-06-07
84.3
best: 97.76 (PointGST)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· 2017-06-07
77.9
best: 97.2 (OmniVec2)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononIntrA
F1 score (5-fold)· 2017-06-07
0.903
best: 0.936 (3DMedPT)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononModelNet40-C
Error Rate· 2017-06-07
0.236
best: 0.142 (OmniVec2)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Standard Deviation· 2017-06-07
16
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononScanObjectNN
GFLOPs· 2017-06-07
1.7
best: 45 (PCM)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy (PB_T50_RS)· 2017-06-07
77.9
best: 92.64 (Mamba3D)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Semantic SegmentationonToronto-3D
OA· 2020-03-18
91.21
best: 95.5 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
3D Semantic SegmentationonToronto-3D
mIoU· 2020-03-18
56.55
best: 73.6 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· 2017-06-07
90.7
best: 95.3 (PointGST)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Overall Accuracy· 2017-06-07
18.8
best: 96.5 (ReCon++)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Standard Deviation· 2017-06-07
7
best: 13.5 (PointNet)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Overall Accuracy· 2017-06-07
38.53
best: 98 (PointGPT)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Overall Accuracy· 2017-06-07
23.05
best: 95 (Point-JEPA)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Standard Deviation· 2017-06-07
7
best: 13.5 (PointNet)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Overall Accuracy· 2017-06-07
42.39
best: 99.5 (ReCon++)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Standard Deviation· 2017-06-07
14.2
best: 15.5 (PointNet)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Shape Representation Of 3D Point CloudsonScanObjectNN
Number of params (M)· 2017-06-07
1.5
best: 34.2 (PCM)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· 2017-06-07
90.7
best: 95.3 (PointGST)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Overall Accuracy· 2017-06-07
18.8
best: 96.5 (ReCon++)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Standard Deviation· 2017-06-07
7
best: 13.5 (PointNet)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Overall Accuracy· 2017-06-07
38.53
best: 98 (PointGPT)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Overall Accuracy· 2017-06-07
23.05
best: 95 (Point-JEPA)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Standard Deviation· 2017-06-07
7
best: 13.5 (PointNet)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Overall Accuracy· 2017-06-07
42.39
best: 99.5 (ReCon++)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Standard Deviation· 2017-06-07
14.2
best: 15.5 (PointNet)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ClassificationonScanObjectNN
Number of params (M)· 2017-06-07
1.5
best: 34.2 (PCM)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· 2017-06-07
90.7
best: 95.3 (PointGST)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Overall Accuracy· 2017-06-07
18.8
best: 96.5 (ReCon++)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Standard Deviation· 2017-06-07
7
best: 13.5 (PointNet)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Overall Accuracy· 2017-06-07
38.53
best: 98 (PointGPT)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Overall Accuracy· 2017-06-07
23.05
best: 95 (Point-JEPA)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Standard Deviation· 2017-06-07
7
best: 13.5 (PointNet)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Overall Accuracy· 2017-06-07
42.39
best: 99.5 (ReCon++)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Standard Deviation· 2017-06-07
14.2
best: 15.5 (PointNet)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
3D Point Cloud ReconstructiononScanObjectNN
Number of params (M)· 2017-06-07
1.5
best: 34.2 (PCM)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413

Medical17 results

Semantic SegmentationonScanNet
test mIoU· 2017-06-07
33.9
best: 79.8 (PTv3 ARKit LabelMaker)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonScanNet
val mIoU· 2017-06-07
53.5
best: 80.5 (DITR)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonToronto-3D L002
mIoU· 2017-06-07
56.5
best: 81.13 (EyeNet)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonToronto-3D L002
oAcc· 2017-06-07
91.2
best: 94.63 (EyeNet)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonDALES
Overall Accuracy· 2017-06-07
95.7
best: 97.8 (KPConv)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonDALES
mIoU· 2017-06-07
68.3
best: 81.1 (KPConv)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonSTPLS3D
mIOU· 2017-06-07
15.92
best: 53.73 (KpConv)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonKITTI-360
mIoU Category· 2017-06-07
58.28
best: 74.08 (MinkowskiNet)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonKITTI-360
miou· 2017-06-07
35.66
best: 58.3 (DeepViewAgg)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonIntrA
DSC (A)· 2017-06-07
84.64
best: 89.71 (3DMedPT)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonIntrA
DSC (V)· 2017-06-07
96.48
best: 97.29 (3DMedPT)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonIntrA
IoU (A)· 2017-06-07
76.38
best: 82.39 (3DMedPT)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonIntrA
IoU (V)· 2017-06-07
93.42
best: 94.82 (3DMedPT)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonToronto-3D
OA· 2020-03-18
91.21
best: 95.5 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
Semantic SegmentationonToronto-3D
mIoU· 2020-03-18
56.55
best: 73.6 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
Semantic SegmentationonShapeNet-Part
Class Average IoU· 2017-06-07
81.9
best: 87.7 (Feature Geometric Net (FG-Net))
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
Semantic SegmentationonShapeNet-Part
Instance Average IoU· 2017-06-07
85.1
best: 89.1 (GeomGCNN)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413

Audio17 results

10-shot image generationonScanNet
test mIoU· 2017-06-07
33.9
best: 79.8 (PTv3 ARKit LabelMaker)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonScanNet
val mIoU· 2017-06-07
53.5
best: 80.5 (DITR)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonToronto-3D L002
mIoU· 2017-06-07
56.5
best: 81.13 (EyeNet)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonToronto-3D L002
oAcc· 2017-06-07
91.2
best: 94.63 (EyeNet)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonDALES
Overall Accuracy· 2017-06-07
95.7
best: 97.8 (KPConv)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonDALES
mIoU· 2017-06-07
68.3
best: 81.1 (KPConv)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonSTPLS3D
mIOU· 2017-06-07
15.92
best: 53.73 (KpConv)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonKITTI-360
mIoU Category· 2017-06-07
58.28
best: 74.08 (MinkowskiNet)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonKITTI-360
miou· 2017-06-07
35.66
best: 58.3 (DeepViewAgg)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonIntrA
DSC (A)· 2017-06-07
84.64
best: 89.71 (3DMedPT)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonIntrA
DSC (V)· 2017-06-07
96.48
best: 97.29 (3DMedPT)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonIntrA
IoU (A)· 2017-06-07
76.38
best: 82.39 (3DMedPT)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonIntrA
IoU (V)· 2017-06-07
93.42
best: 94.82 (3DMedPT)
SOTA
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonToronto-3D
OA· 2020-03-18
91.21
best: 95.5 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
10-shot image generationonToronto-3D
mIoU· 2020-03-18
56.55
best: 73.6 (SCF-Net)
Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways arXiv:2003.08284
10-shot image generationonShapeNet-Part
Class Average IoU· 2017-06-07
81.9
best: 87.7 (Feature Geometric Net (FG-Net))
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413
10-shot image generationonShapeNet-Part
Instance Average IoU· 2017-06-07
85.1
best: 89.1 (GeomGCNN)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space arXiv:1706.02413