[HTML][HTML] Self-supervised learning for point cloud data: A survey

C Zeng, W Wang, A Nguyen, J **ao, Y Yue - Expert Systems with …, 2024 - Elsevier
Abstract 3D point clouds are a crucial type of data collected by LiDAR sensors and widely
used in transportation applications due to its concise descriptions and accurate localization …

Self-supervised learning for pre-training 3d point clouds: A survey

B Fei, W Yang, L Liu, T Luo, R Zhang, Y Li… - arxiv preprint arxiv …, 2023 - arxiv.org
Point cloud data has been extensively studied due to its compact form and flexibility in
representing complex 3D structures. The ability of point cloud data to accurately capture and …

Masked surfel prediction for self-supervised point cloud learning

Y Zhang, J Lin, C He, Y Chen, K Jia… - arxiv preprint arxiv …, 2022 - arxiv.org
Masked auto-encoding is a popular and effective self-supervised learning approach to point
cloud learning. However, most of the existing methods reconstruct only the masked points …

3D shape contrastive representation learning with adversarial examples

C Wen, X Li, H Huang, YS Liu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Current supervised methods for 3D shape representation learning have achieved satisfying
performance, yet require extensive human-labeled datasets. Unsupervised learning-based …

Point-dae: Denoising autoencoders for self-supervised point cloud learning

Y Zhang, J Lin, R Li, K Jia, L Zhang - arxiv preprint arxiv:2211.06841, 2022 - arxiv.org
Masked autoencoder has demonstrated its effectiveness in self-supervised point cloud
learning. Considering that masking is a kind of corruption, in this work we explore a more …

Towards robustness and generalization of point cloud representation: A geometry coding method and a large-scale object-level dataset

M Xu, Z Zhou, Y Wang, Y Qiao - Computational Visual Media, 2024 - Springer
Robustness and generalization are two challenging problems for learning point cloud
representation. To tackle these problems, we first design a novel geometry coding model …

Self-Supervised Pretraining Framework for Extracting Global Structures From Building Point Clouds via Completion

H Yang, R Wang - IEEE Transactions on Geoscience and …, 2024 - ieeexplore.ieee.org
The exterior structural information of buildings are crucial for advancing smart city initiatives
and reconstructing 3-D edifices. However, practical obstacles, such as sparse or incomplete …

Point‐AGM: Attention Guided Masked Auto‐Encoder for Joint Self‐supervised Learning on Point Clouds

J Liu, M Yang, Y Tian, Y Li, D Song… - Computer Graphics …, 2024 - Wiley Online Library
Masked point modeling (MPM) has gained considerable attention in self‐supervised
learning for 3D point clouds. While existing self‐supervised methods have progressed in …

PointAS: an attention based sampling neural network for visual perception

B Qiu, S Li, L Wang - Frontiers in Computational Neuroscience, 2024 - frontiersin.org
Harnessing the remarkable ability of the human brain to recognize and process complex
data is a significant challenge for researchers, particularly in the domain of point cloud …

PMT-MAE: Dual-Branch Self-Supervised Learning with Distillation for Efficient Point Cloud Classification

Q Zheng, C Zhang, J Sun - arxiv preprint arxiv:2409.02007, 2024 - arxiv.org
Advances in self-supervised learning are essential for enhancing feature extraction and
understanding in point cloud processing. This paper introduces PMT-MAE (Point MLP …