3D Place Recognition On Oxford Robotcar
Metrics
AR@1
AR@1%
Results
Performance results of various models on this benchmark
Model Name | AR@1 | AR@1% | Paper Title | Repository |
|---|---|---|---|---|
| DH3D | 74.2 | 85.3 | DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization | |
| CrossLoc3D | 94.36 | 98.59 | CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition | |
| LPD-Net | 86.3 | 94.9 | LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis | |
| PCAN | - | 83.8 | PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval | |
| PPT-Net | 93.5 | 98.1 | Pyramid Point Cloud Transformer for Large-Scale Place Recognition | |
| pointnetvlad | - | 80.3 | PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition | |
| soe-net | - | 96.4 | SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition | |
| Minkloc3D | 93.0 | 97.9 | - | - |
| SVT-Net | 93.7 | 97.8 | SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition | - |
| Minkloc3D-S | 82.0 | 93.1 | MinkLoc3D-SI: 3D LiDAR place recognition with sparse convolutions, spherical coordinates, and intensity |
0 of 10 row(s) selected.