HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Point Cloud Registration On 3Dmatch Benchmark

평가 지표

Feature Matching Recall

평가 결과

이 벤치마크에서 각 모델의 성능 결과

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

0 of 15 row(s) selected.