2019 IEEE International Conference on Multimedia and Expo (ICME) 2019
DOI: 10.1109/icme.2019.00268
|View full text |Cite
|
Sign up to set email alerts
|

Fast Registration for Cross-Source Point Clouds by using Weak Regional Affinity and Pixel-Wise Refinement

Abstract: Many types of 3D acquisition sensors are emerged in recent years and point cloud has been widely used in many areas. Accurate and fast registration of cross-source 3D point clouds from different sensors is an emerged research problem in computer vision. This problem is extremely challenging because cross-source point clouds contain mixture of various variances, such as density, partial overlap, large noise and outliers, viewpoint changing. In this paper, an algorithm is proposed to align cross-source point clo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
17
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
2
2

Relationship

1
6

Authors

Journals

citations
Cited by 24 publications
(17 citation statements)
references
References 16 publications
0
17
0
Order By: Relevance
“…CSGM [41] converts the registration problem into a graph matching problem and estimate the transformation matrix by graph matching optimization. Recently, [39] introduce highorder constraints to correspondences searching and convert the registration problem into a tensor optimization problem. RSER [69] proposes a scale estimation method and use RANSAC to calculate the transformation after scale normalization.…”
Section: A Optimization-based Methodsmentioning
confidence: 99%
See 3 more Smart Citations
“…CSGM [41] converts the registration problem into a graph matching problem and estimate the transformation matrix by graph matching optimization. Recently, [39] introduce highorder constraints to correspondences searching and convert the registration problem into a tensor optimization problem. RSER [69] proposes a scale estimation method and use RANSAC to calculate the transformation after scale normalization.…”
Section: A Optimization-based Methodsmentioning
confidence: 99%
“…Since [77] uses ICP, [42] uses Gaussian mixture model alignment, [69] uses RANSAC to solve the cross-source registration problem, we only compare their registration parts. We also re-implement and compare with GCTR [39], which is a recent work focus on cross-source point cloud registration. Due to the huge memory cost of Gaussian mixture model and huge computation cost of GCTR, we follow their original papers to uniform sample the original point clouds to approximately 2000 and 200 for GMM alignment [42] and GCTR [39] respectively.…”
Section: Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…Correspondence outliers are the wrong correspondence. Regarding the correspondence outlier rejection, there are mainly two kinds of algorithms: conventional methods [5], [6], [7], [8], [9], [10], [11] and learning-based methods [1], [2], [3],…”
Section: Introductionmentioning
confidence: 99%