Point Cloud Registration On Eth Trained On
Metrics
Feature Matching Recall
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Feature Matching Recall |
|---|---|
| learning-compact-geometric-features | 0.202 |
| distinctive-3d-local-deep-descriptors | 0.928 |
| generalisable-and-distinctive-3d-local-deep | 0.982 |
| fast-point-feature-histograms-fpfh-for-3d | 0.221 |
| fully-convolutional-geometric-features | 0.161 |
| d3feat-joint-learning-of-dense-detection-and | 0.563 |
| the-perfect-match-3d-point-cloud-matching | 0.790 |
| challenging-the-universal-representation-of | 0.784 |
| 3dmatch-learning-local-geometric-descriptors | 0.169 |
| addressing-the-generalization-of-3d | - |
| sc2-pcr-a-second-order-spatial-compatibility | - |
| you-only-hypothesize-once-point-cloud | - |
| pointdsc-robust-point-cloud-registration | - |
| sc2-pcr-a-second-order-spatial-compatibility | - |
| geotransformer-fast-and-robust-point-cloud | - |
| end-to-end-learning-local-multi-view | 0.616 |
| pointdsc-robust-point-cloud-registration | - |
| you-only-hypothesize-once-point-cloud | - |
| go-icp-a-globally-optimal-solution-to-3d-icp | - |
| spinnet-learning-a-general-surface-descriptor | 0.928 |