Point Cloud Registration On Eth Trained On

Metrics

Feature Matching Recall

Results

Performance results of various models on this benchmark

Model Name	Feature Matching Recall	Paper Title	Repository
CGF	0.202	Learning Compact Geometric Features	-
DIP	0.928	Distinctive 3D local deep descriptors	-
GeDi	0.982	Learning general and distinctive 3D local deep descriptors for point cloud registration	-
FPFH	0.221	Fast Point Feature Histograms (FPFH) for 3D Registration
FCGF	0.161	Fully Convolutional Geometric Features
D3Feat-pred	0.563	D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features	-
PerfectMatch	0.790	The Perfect Match: 3D Point Cloud Matching with Smoothed Densities	-
Greedy Grid Search	0.784	Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration	-
3DMatch	0.169	3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions	-
Exhaustive Grid Search	-	Addressing the generalization of 3D registration methods with a featureless baseline and an unbiased benchmark
FCGF+SC2-PCR	-	SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration	-
YOHO-O	-	You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors	-
FPFH+PointDSC	-	PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency	-
FPFH+SC2-PCR	-	SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration	-
GeoTransformer	-	GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer	-
LMVD	0.616	End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds	-
FCGF+PointDSC	-	PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency	-
YOHO-C	-	You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors	-
GO-ICP	-	Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration	-
SpinNet	0.928	SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration	-

0 of 20 row(s) selected.