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/ReCon++

ReCon++

Reported on 43 benchmarks across 4 tasks · 1 paper · 22 SOTA

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

Computer Vision43 results

Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-BG (OA)· uses extra data· 2024-02-27
98.8
best: 99.48 (PointGST)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2024-02-27
97.59
best: 97.76 (PointGST)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonModelNet40
Overall Accuracy· uses extra data· 2024-02-27
95
best: 95.3 (PointGST)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2024-02-27
96.5
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2024-02-27
94.5
best: 95 (Point-JEPA)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2024-02-27
99.5
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonScanObjectNN
OBJ_ONLY Accuracy(%)· uses extra data· 2024-02-27
65.4
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonScanObjectNN
OBJ-BG (OA)· uses extra data· 2024-02-27
98.8
best: 99.48 (PointGST)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2024-02-27
97.59
best: 97.76 (PointGST)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonModelNet40
Overall Accuracy· uses extra data· 2024-02-27
95
best: 95.3 (PointGST)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2024-02-27
96.5
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2024-02-27
94.5
best: 95 (Point-JEPA)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2024-02-27
99.5
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonScanObjectNN
OBJ_ONLY Accuracy(%)· uses extra data· 2024-02-27
65.4
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud Linear ClassificationonModelNet40
Overall Accuracy· 2024-02-27
93.6
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononScanObjectNN
OBJ-BG (OA)· uses extra data· 2024-02-27
98.8
best: 99.48 (PointGST)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononScanObjectNN
OBJ-ONLY (OA)· uses extra data· 2024-02-27
97.59
best: 97.76 (PointGST)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononModelNet40
Overall Accuracy· uses extra data· 2024-02-27
95
best: 95.3 (PointGST)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2024-02-27
96.5
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2024-02-27
94.5
best: 95 (Point-JEPA)
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2024-02-27
99.5
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononScanObjectNN
OBJ_ONLY Accuracy(%)· uses extra data· 2024-02-27
65.4
SOTA
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· uses extra data· 2024-02-27
95.25
best: 97.2 (OmniVec2)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2024-02-27
3
best: 13.5 (PointNet)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2024-02-27
98
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2024-02-27
2.3
best: 16 (PointNet++)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2024-02-27
4.1
best: 13.5 (PointNet)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2024-02-27
0.8
best: 15.5 (PointNet)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
Shape Representation Of 3D Point CloudsonModelNet40
Accuracy (%)· uses extra data· 2024-02-27
87.3
best: 88.2 (Uni3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· uses extra data· 2024-02-27
95.25
best: 97.2 (OmniVec2)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2024-02-27
3
best: 13.5 (PointNet)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2024-02-27
98
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2024-02-27
2.3
best: 16 (PointNet++)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2024-02-27
4.1
best: 13.5 (PointNet)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2024-02-27
0.8
best: 15.5 (PointNet)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ClassificationonModelNet40
Accuracy (%)· uses extra data· 2024-02-27
87.3
best: 88.2 (Uni3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· uses extra data· 2024-02-27
95.25
best: 97.2 (OmniVec2)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2024-02-27
3
best: 13.5 (PointNet)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2024-02-27
98
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2024-02-27
2.3
best: 16 (PointNet++)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2024-02-27
4.1
best: 13.5 (PointNet)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2024-02-27
0.8
best: 15.5 (PointNet)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766
3D Point Cloud ReconstructiononModelNet40
Accuracy (%)· uses extra data· 2024-02-27
87.3
best: 88.2 (Uni3D)
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction arXiv:2402.17766