HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Point Cloud Registration On 3Dmatch Benchmark

評価指標

Feature Matching Recall

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Feature Matching Recall
Paper TitleRepository
D3Feat-Pred95.8D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
3DSmoothNet94.7The Perfect Match: 3D Point Cloud Matching with Smoothed Densities
PPF-FoldNet71.8PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors
D3Feat-rand95.3D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
IMFNet98.6IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration
FCGF + RANSAC85Fully Convolutional Geometric Features
MS-SVConv98.43D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning
DIP94.8Distinctive 3D local deep descriptors
FPFH + RANSAC44.2Fast Point Feature Histograms (FPFH) for 3D Registration
SpinNet (no code published as of Dec 15 2020)97.6SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
3DMatch + RANSAC66.83DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
GeDi (no code published as of May 27 2021)97.9Learning general and distinctive 3D local deep descriptors for point cloud registration
DIP + Point-TnT96.8Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition
LMVD97.5End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
PPFNet62.3PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
0 of 15 row(s) selected.