HyperAI초신경

Point Cloud Registration On 3Dmatch Benchmark

평가 지표

Feature Matching Recall

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
IMFNet	98.6	IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration
MS-SVConv	98.4	3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning
GeDi (no code published as of May 27 2021)	97.9	Learning general and distinctive 3D local deep descriptors for point cloud registration
SpinNet (no code published as of Dec 15 2020)	97.6	SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
LMVD	97.5	End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
DIP + Point-TnT	96.8	Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition
D3Feat-Pred	95.8	D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
D3Feat-rand	95.3	D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
DIP	94.8	Distinctive 3D local deep descriptors
3DSmoothNet	94.7	The Perfect Match: 3D Point Cloud Matching with Smoothed Densities
FCGF + RANSAC	85	Fully Convolutional Geometric Features
PPF-FoldNet	71.8	PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors
3DMatch + RANSAC	66.8	3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
PPFNet	62.3	PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
FPFH + RANSAC	44.2	Fast Point Feature Histograms (FPFH) for 3D Registration

0 of 15 row(s) selected.