HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Point Cloud Registration On 3Dlomatch 10 30

Metrics

Recall ( correspondence RMSE below 0.2)

Results

Performance results of various models on this benchmark

Model Name
Recall ( correspondence RMSE below 0.2)
Paper TitleRepository
REGTR64.8REGTR: End-to-end Point Cloud Correspondences with Transformers-
3DSN (reported in PREDATOR)33The Perfect Match: 3D Point Cloud Matching with Smoothed Densities-
PCAM (reported in REGTR)54.9PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds-
DGR (reported in REGTR)48.7Deep Global Registration-
FCGF (reported in PREDATOR)40.1Fully Convolutional Geometric Features
D3Feat (reported in PREDATOR)37.2D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features-
Predator-1k62.5PREDATOR: Registration of 3D Point Clouds with Low Overlap-
OMNet (reported in REGTR)8.4OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration-
NgeNet71.9Leveraging Inlier Correspondences Proportion for Point Cloud Registration-
GeoTransformer - P2PNet74Geometric Transformer for Fast and Robust Point Cloud Registration-
Predator-5k59.8PREDATOR: Registration of 3D Point Clouds with Low Overlap-
Predator-NR24PREDATOR: Registration of 3D Point Clouds with Low Overlap-
0 of 12 row(s) selected.
Point Cloud Registration On 3Dlomatch 10 30 | SOTA | HyperAI