Unsupervised deep probabilistic approach for partial point cloud registration

G Mei, H Tang, X Huang, W Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Deep point cloud registration methods face challenges to partial overlaps and rely on
labeled data. To address these issues, we propose UDPReg, an unsupervised deep …

Review on deep learning algorithms and benchmark datasets for pairwise global point cloud registration

Y Zhao, L Fan - Remote Sensing, 2023 - mdpi.com
Point cloud registration is the process of aligning point clouds collected at different locations
of the same scene, which transforms the data into a common coordinate system and forms …

Bringing masked autoencoders explicit contrastive properties for point cloud self-supervised learning

B Ren, G Mei, DP Paudel, W Wang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved
performance comparable to CL for traditional convolutional backbones. However, in 3D …

MAC: Maximal Cliques for 3D Registration

J Yang, X Zhang, P Wang, Y Guo, K Sun… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
This paper presents a 3D registration method with maximal cliques (MAC) for 3D point cloud
registration (PCR). The key insight is to loosen the previous maximum clique constraint and …

Unsupervised Point Cloud Representation Learning by Clustering and Neural Rendering

G Mei, C Saltori, E Ricci, N Sebe, Q Wu… - International Journal of …, 2024 - Springer
Data augmentation has contributed to the rapid advancement of unsupervised learning on
3D point clouds. However, we argue that data augmentation is not ideal, as it requires a …

RRGA-Net: Robust Point Cloud Registration Based on Graph Convolutional Attention

J Qian, D Tang - Sensors, 2023 - mdpi.com
The problem of registering point clouds in scenarios with low overlap is explored in this
study. Previous methodologies depended on having a sufficient number of repeatable …

Automatic registration of large-scale building point clouds with high outlier rates

R Li, S Gan, X Yuan, R Bi, W Luo, C Chen… - Automation in …, 2024 - Elsevier
Point cloud registration plays a crucial role in processing large-scale building point cloud
data. However, existing registration algorithms face challenges in effectively handling …

Data augmentation-free unsupervised learning for 3d point cloud understanding

G Mei, C Saltori, F Poiesi, J Zhang, E Ricci… - arxiv preprint arxiv …, 2022 - arxiv.org
Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially
thanks to data augmentation-based contrastive methods. However, data augmentation is not …

Deep learning-based low overlap point cloud registration for complex scenario: The review

Y Zhao, J Zhang, S Xu, J Ma - Information Fusion, 2024 - Elsevier
Most studies on point cloud registration have established the problem in the case of ideal
point cloud data. Although the state-of-the-art approaches have achieved amazing results …

Semantic enhancement based adaptive geometric encoding network for low overlap point cloud registration

Y Zhao, J Zhang, S Xu, J Ma, H Wang - Displays, 2024 - Elsevier
The presence of partial or low overlaps in real point cloud pairs poses significant challenges
to obtain robust registration. There is an absence of a unified framework that localizes …