HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Point Cloud Registration On 3Dlomatch 10 30

Metrics

Recall ( correspondence RMSE below 0.2)

Results

Performance results of various models on this benchmark

Paper Title
GeoTransformer - P2PNet74Geometric Transformer for Fast and Robust Point Cloud Registration
NgeNet71.9Leveraging Inlier Correspondences Proportion for Point Cloud Registration
REGTR64.8REGTR: End-to-end Point Cloud Correspondences with Transformers
Predator-1k62.5PREDATOR: Registration of 3D Point Clouds with Low Overlap
Predator-5k59.8PREDATOR: Registration of 3D Point Clouds with Low Overlap
PCAM (reported in REGTR)54.9PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds
DGR (reported in REGTR)48.7Deep Global Registration
FCGF (reported in PREDATOR)40.1Fully Convolutional Geometric Features
D3Feat (reported in PREDATOR)37.2D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
3DSN (reported in PREDATOR)33The Perfect Match: 3D Point Cloud Matching with Smoothed Densities
Predator-NR24PREDATOR: Registration of 3D Point Clouds with Low Overlap
OMNet (reported in REGTR)8.4OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration
0 of 12 row(s) selected.
Point Cloud Registration On 3Dlomatch 10 30 | SOTA | HyperAI