Unsupervised deep probabilistic approach for partial point cloud registration
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 …
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 …
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
Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved
performance comparable to CL for traditional convolutional backbones. However, in 3D …
performance comparable to CL for traditional convolutional backbones. However, in 3D …
MAC: Maximal Cliques for 3D Registration
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 …
registration (PCR). The key insight is to loosen the previous maximum clique constraint and …
Unsupervised Point Cloud Representation Learning by Clustering and Neural Rendering
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 …
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 …
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. However, existing registration algorithms face challenges in effectively handling …
Data augmentation-free unsupervised learning for 3d point cloud understanding
Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially
thanks to data augmentation-based contrastive methods. However, data augmentation is not …
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
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 …
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
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 …
to obtain robust registration. There is an absence of a unified framework that localizes …