HyperAI초신경

Point Cloud Registration On Kitti Trained On

평가 지표

Success Rate

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
GeDi	98.92	Learning general and distinctive 3D local deep descriptors for point cloud registration
FCGF+SC2-PCR	97.66	SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration
FCGF+PointDSC	96.76	PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
Exhaustive Grid Search	94.95	Addressing the generalization of 3D registration methods with a featureless baseline and an unbiased benchmark
FPFH+PointDSC	94.05	PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
DIP	93.51	Distinctive 3D local deep descriptors
Greedy Grid Search	90.27	Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration
YOHO-C	82.16	You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
YOHO-O	81.44	You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
SpinNet	81.44	SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
GeoTransformer	67.93	GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer
Predator	41.20	PREDATOR: Registration of 3D Point Clouds with Low Overlap
D3Feat-pred	36.76	D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
FCGF	24.19	Fully Convolutional Geometric Features

0 of 14 row(s) selected.