2021 IEEE/CVF International Conference on Computer Vision (ICCV) 2021
DOI: 10.1109/iccv48922.2021.01571
|View full text |Cite
|
Sign up to set email alerts
|

HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
28
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 89 publications
(28 citation statements)
references
References 24 publications
0
28
0
Order By: Relevance
“…We further compare to three RANSAC-free methods in Tab. 5(bottom): FMR [16], DGR [7] and HRegNet [21]. Our method outperforms all the baselines by large margin.…”
Section: Outdoor Benchmark: Kitti Odometrymentioning
confidence: 99%
See 1 more Smart Citation
“…We further compare to three RANSAC-free methods in Tab. 5(bottom): FMR [16], DGR [7] and HRegNet [21]. Our method outperforms all the baselines by large margin.…”
Section: Outdoor Benchmark: Kitti Odometrymentioning
confidence: 99%
“…Following [4,8,15,21,39], we compute the mean RRE and the mean RTE only for the correctly registered point cloud pairs in KITTI.…”
Section: B2 Kittimentioning
confidence: 99%
“…Various such descriptor have been suggested, e.g. [10,18,20]. Fully Convolutional Geometric Features (FCGF) [10] are based on sparse convolutions over a voxelized represen-tation of the point cloud.…”
Section: Related Workmentioning
confidence: 99%
“…One approach for producing a harder benchmark is to replace the LiDAR dataset. In [20], for example, they use the more challenging NuScenes [6] dataset. However, framepairs are still selected with a simple heuristic: scans separated by one second.…”
Section: Introductionmentioning
confidence: 99%
“…Anyhow, they are usually considered as a coarse registration to provide an initial guess for fine registration. In hybrid models [10], [11], they assemble different registration modules to achieve a coarse-tofine result. In contrast to feature matching-based registrations, global feature registrations are more direct.…”
Section: Introductionmentioning
confidence: 99%