Recall ( correspondence RMSE below 0.2): 62.5
Papers with Code · CC BY-SA 4.0
Point Cloud Registration
Point Cloud Registration is a fundamental problem in 3D computer vision and photogrammetry. Given several sets of points in different coordinate systems, the aim of registration is to find the transformation that best aligns all of them into a common coordinate system. Point Cloud Registration plays a significant role in many vision applications such as 3D model reconstruction, cultural heritage management, landslide monitoring and solar energy analysis.
<span class="description-source">Source: Iterative Global Similarity Points : A robust coarse-to-fine integration solution for pairwise 3D point cloud registration </span>
논문
mRR @ Normal Criterion (1.5°&0.3m): 78.2RR @ Loose Criterion (5°&2m), on LoKITTI: 50.8
Recall: 0.627
mRR @ Normal Criterion (1.5°&0.3m): 88.8RR @ Loose Criterion (5°&2m), on LoKITTI: 55.4
Recall: 0.325
Recall: 0.922
Recall (3cm, 10 degrees): 99.64RRE (degrees): 0.95RTE (cm): 0.43
Recall (3cm, 10 degrees): 99.64RRE (degrees): 0.005RTE (cm): 0.002
Recall ( correspondence RMSE below 0.2): 81.6
Recall ( correspondence RMSE below 0.2): 48.7
Recall: 0.136
Recall ( correspondence RMSE below 0.2): 74
Recall (3cm, 10 degrees): 64.12RRE (degrees): 2.29RTE (cm): 1.57
Recall (3cm, 10 degrees): 0.00RRE (degrees): -RTE (cm): -
Recall ( correspondence RMSE below 0.2): 71.9
Recall ( correspondence RMSE below 0.2): 8.4
Recall ( correspondence RMSE below 0.2): 54.9
Recall ( correspondence RMSE below 0.2): 64.8
CD: 0.0083RRE: 0.510RTE: 1.27
CD: 0.0111RRE: 1.012RTE: 1.67
Recall: 0.845
Recall ( correspondence RMSE below 0.2): 33