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

Huang, Xiaoshui; Li, Fan; Wu, Qiang; Zhang, Jian; Yuan, Chun

doi:10.1109/icme.2019.00268

Cited by 24 publications

(17 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

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%

“…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%

“…According to [77], [41], cross-source point cloud registration is much more challenging because of the combination of considerable noise and outliers, density difference, partial overlap and scale difference. Several algorithms [42], [41], [43], [39] use sophisticated optimization strategies to solve the crosssource point cloud registration problem by overcoming the cross-source challenges. For example, CSGM [41] transforms the registration problem into a graph matching problem and leverage the graph matching theory to overcome these challenges.…”

Section: Cross-source Registrationmentioning

confidence: 99%

“…The above literature review shows that most of the current research focuses on same-source point cloud registration. While several existing methods [77], [42], [69], [39] are targeted on cross-source domains, the accuracy is low and…”

Section: New Cross-source Benchmarkmentioning

confidence: 99%

See 3 more Smart Citations

A comprehensive survey on point cloud registration

Huang

Mei

Zhang

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Registration is a transformation estimation problem between two point clouds, which has a unique and critical role in numerous computer vision applications. The developments of optimization-based methods and deep learning methods have improved registration robustness and efficiency. Recently, the combinations of optimization-based and deep learning methods have further improved performance. However, the connections between optimization-based and deep learning methods are still unclear. Moreover, with the recent development of 3D sensors and 3D reconstruction techniques, a new research direction emerges to align cross-source point clouds. This survey conducts a comprehensive survey, including both same-source and cross-source registration methods, and summarize the connections between optimization-based and deep learning methods, to provide further research insight. This survey also builds a new benchmark to evaluate the state-of-the-art registration algorithms in solving cross-source challenges. Besides, this survey summarizes the benchmark data sets and discusses point cloud registration applications across various domains. Finally, this survey proposes potential research directions in this rapidly growing field.

show abstract

Section: A Optimization-based Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Cross-source Registrationmentioning

confidence: 99%

Section: New Cross-source Benchmarkmentioning

confidence: 99%

See 2 more Smart Citations

A comprehensive survey on point cloud registration

Huang

Mei

Zhang

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…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%

GMF: General Multimodal Fusion Framework for Correspondence Outlier Rejection

Huang¹,

Qu²,

Zuo³

et al. 2022

Preprint

View full text Add to dashboard Cite

Rejecting correspondence outliers enables to boost the correspondence quality, which is a critical step in achieving high point cloud registration accuracy. The current state-ofthe-art correspondence outlier rejection methods only utilize the structure features of the correspondences. However, texture information is critical to reject the correspondence outliers in our human vision system. In this paper, we propose General Multimodal Fusion (GMF) to learn to reject the correspondence outliers by leveraging both the structure and texture information. Specifically, two cross-attention-based fusion layers are proposed to fuse the texture information from paired images and structure information from point correspondences. Moreover, we propose a convolutional position encoding layer to enhance the difference between T okens and enable the encoding feature pay attention to neighbor information. Our position encoding layer will make the cross-attention operation integrate both local and global information. Experiments on multiple datasets(3DMatch, 3DLoMatch, KITTI) and recent state-of-the-art models (3DRegNet, DGR, PointDSC) prove that our GMF achieves wide generalization ability and consistently improves the point cloud registration accuracy. Furthermore, several ablation studies demonstrate the robustness of the proposed GMF on different loss functions, lighting conditions and noises. The code is available at https: //github.com/XiaoshuiHuang/GMF.

show abstract

Point Cloud Registration Based on Global and Local Feature Fusion

Yue

Yuan

et al. 2022

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Cross-modality point cloud registration is confronted with significant challenges due to inherent differences in modalities between different sensors. We propose a cross-modality point cloud registration framework FF-LOGO: a cross-modality point cloud registration method with feature filtering and local-global optimization. The crossmodality feature correlation filtering module extracts geometric transformation-invariant features from cross-modality point clouds and achieves point selection by feature matching. We also introduce a cross-modality optimization process, including a local adaptive key region aggregation module and a global modality consistency fusion optimization module. Experimental results demonstrate that our two-stage optimization significantly improves the registration accuracy of the feature association and selection module. Our method achieves a substantial increase in recall rate compared to the current state-of-the-art methods on the 3DCSR dataset, improving from 40.59% to 75.74%. Our code will be available at https://github.com/wangmohan17/FFLOGO.

show abstract

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

Cited by 24 publications

References 16 publications

A comprehensive survey on point cloud registration

A comprehensive survey on point cloud registration

GMF: General Multimodal Fusion Framework for Correspondence Outlier Rejection

Point Cloud Registration Based on Global and Local Feature Fusion

Contact Info

Product

Resources

About