2021 IEEE/CVF International Conference on Computer Vision (ICCV) 2021
DOI: 10.1109/iccv48922.2021.01569
|View full text |Cite
|
Sign up to set email alerts
|

Deep Hough Voting for Robust Global Registration

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
14
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
3
2

Relationship

0
10

Authors

Journals

citations
Cited by 79 publications
(14 citation statements)
references
References 44 publications
0
14
0
Order By: Relevance
“…We further compare with recent deep robust estimators: 3DRegNet [22], DGR [7], PointDSC [3], DHVR [18] and PCAM [6] on 3DMatch and KITTI. Following common practice, we report RTE, RRE and RR on both benchmarks.…”
Section: D2 Comparison With Deep Robust Estimatorsmentioning
confidence: 99%
“…We further compare with recent deep robust estimators: 3DRegNet [22], DGR [7], PointDSC [3], DHVR [18] and PCAM [6] on 3DMatch and KITTI. Following common practice, we report RTE, RRE and RR on both benchmarks.…”
Section: D2 Comparison With Deep Robust Estimatorsmentioning
confidence: 99%
“…Beyond the former types of methods that require the network to implicitly remember the target objects during train-ing, registration based methods [2,15,16,33,46,55,59] treat this task as point cloud registration and could estimate the 6D pose between two novel inputs. However, they usually consider the registration between two similar-sized targets.…”
Section: Object 6d Pose Estimation Algorithmsmentioning
confidence: 99%
“…RGM [FLLW21] introduces a deep graph matching‐based framework for registration, which takes both local geometry and graph topological structure into consideration. By contrast, some other methods such as [CDK20, PRG*20, BLZ*21, LKCP21, CSYT22] focus more on the removal of outlier correspondences. For example, DGR [CDK20] and 3DRegNet [PRG*20] utilize a classifier to predict a confidence value for each correspondence.…”
Section: Related Workmentioning
confidence: 99%