PointTr

Reported on 3 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Computer Vision2 results

ReconstructiononCommon Objects in 3D
Avg. F1· 2021-08-19
39.7
best: 83.8 (NU-MCC)
SOTA
PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers arXiv:2108.08839
Single-View 3D ReconstructiononCommon Objects in 3D
Avg. F1· 2021-08-19
39.7
best: 83.8 (NU-MCC)
SOTA
PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers arXiv:2108.08839

Methodology1 result

3DonCommon Objects in 3D
Avg. F1· 2021-08-19
39.7
best: 83.8 (NU-MCC)
SOTA
PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers arXiv:2108.08839