[HTML][HTML] Self-supervised learning for point cloud data: A survey
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 …
used in transportation applications due to its concise descriptions and accurate localization …
Instance-aware dynamic prompt tuning for pre-trained point cloud models
Pre-trained point cloud models have found extensive applications in 3D understanding tasks
like object classification and part segmentation. However, the prevailing strategy of full fine …
like object classification and part segmentation. However, the prevailing strategy of full fine …
Self-supervised learning for pre-training 3d point clouds: A survey
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 …
representing complex 3D structures. The ability of point cloud data to accurately capture and …
To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learning
S Hadgi, L Li, M Ovsjanikov - European Conference on Computer Vision, 2025 - Springer
Transfer learning has long been a key factor in the advancement of many fields including 2D
image analysis. Unfortunately, its applicability in 3D data processing has been relatively …
image analysis. Unfortunately, its applicability in 3D data processing has been relatively …
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 …
learning for 3D point clouds. While existing self‐supervised methods have progressed in …
To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of 3D Transfer Learning
S Hadgi, L Li, M Ovsjanikov - arXiv preprint arXiv:2403.17869, 2024 - arxiv.org
Transfer learning has long been a key factor in the advancement of many fields including 2D
image analysis. Unfortunately, its applicability in 3D data processing has been relatively …
image analysis. Unfortunately, its applicability in 3D data processing has been relatively …
[PDF][PDF] Self-distillation for Efficient Object-level Point Cloud Learning
The emerging accessibility of 3D point cloud data has catalyzed the evolution of deep-
learning methodologies for analysis and processing of 3D data. However, the efficacy of …
learning methodologies for analysis and processing of 3D data. However, the efficacy of …