SCRnet: A Spatial Consistency Guided Network Using Contrastive Learning for Point Cloud Registration

Shao, Huixiang; Zhang, Zhijiang; Feng, Xiaoyu; Zeng, Dan

doi:10.3390/sym14010140

Cited by 5 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These weights are utilized in a weighed SVD to estimate the transformation matrix. Similarly, [23] first calculated the average distance coding and average angle coding from a center point to the neighbor in a sphere cluster. Then, these codings feed into a MLP layer to extract a deep feature Fig.…”

Section: B Learning-based Methodsmentioning

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

Section: B Learning-based Methodsmentioning

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

show abstract

“…As the vehicle moves, the LiDAR captures point cloud information from various perspectives of the target. Therefore, it is necessary to concatenate the front and rear frames to obtain the complete 3D point cloud information of the target [1].…”

Section: Introductionmentioning

confidence: 99%

A Fast Registration Method for MEMS LiDAR Point Cloud Based on Self-Adaptive Segmentation

Li,

Liu,

et al. 2023

Electronics

View full text Add to dashboard Cite

The Micro-Electro-Mechanical System (MEMS) LiDAR point cloud in autonomous vehicles has a large deflection range, which results in slow registration speed and poor applicability. To maximize speed, an improved Normal Distribution Transform (NDT) method that integrates point cloud density features has been proposed. First, the point cloud is reduced using a modified voxel filter and a pass-through filter. Next, the Intrinsic Shape Signature (ISS) algorithm is utilized to analyze the point cloud features and extract key points; the Four-Point Congruent Set (4PCS) algorithm is then employed to calculate the initial pose under the constraints of the key point set to complete the coarse registration. Finally, the self-adaptive segmentation model is constructed by using a K-D tree to obtain the density features of key points, and the NDT algorithm is combined with this model to form an SSM-NDT algorithm, which is used for fine registration. Each algorithm was compared on the autonomous vehicle dataset PandaSet and actual collected datasets. The results show that the novel method increases the speed by at least 60% and takes into account good registration accuracy and strong anti-interference.

show abstract