Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey

Abstract

Deep learning (DL) has become one of the mainstream and effective methods for point cloud analysis tasks such as detection, segmentation and classification. To reduce overfitting during training DL models and improve model performance especially when the amount and/or diversity of training data are limited, augmentation is often crucial. Although various point cloud data augmentation methods have been widely used in different point cloud processing tasks, there are currently no published systematic surveys or reviews of these methods. Therefore, this article surveys these methods, categorizing them into a taxonomy framework that comprises basic and specialized point cloud data augmentation methods. Through a comprehensive evaluation of these augmentation methods, this article identifies their potentials and limitations, serving as a useful reference for choosing appropriate augmentation methods. In addition, potential directions for future research are recommended. This survey contributes to providing a holistic overview of the current state of point cloud data augmentation, promoting its wider application and development.

arXiv commentAccepted by Pattern Recognition

References in corpus (12)

• Neural Discrete Representation Learning
• GelTip: A Finger-shaped Optical Tactile Sensor for Robotic Manipulation
• Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis
• Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Cameras
• Multimodal Virtual Point 3D Detection
• BADet: Boundary-Aware 3D Object Detection from Point Clouds
• Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud
• PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
• Improving Auto-Augment via Augmentation-Wise Weight Sharing
• Weighted Point Cloud Augmentation for Neural Network Training Data Class-Imbalance
• SageMix: Saliency-Guided Mixup for Point Clouds
• 3D Adversarial Augmentations for Robust Out-of-Domain Predictions

Cited by in corpus (6)

• Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery: An Experimental Study
• Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy
• A Survey of Methods for Converting Unstructured Data to CSG Models
• Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images
• MSCrackMamba: Leveraging Vision Mamba for Crack Detection in Fused Multispectral Imagery
• Horticultural Temporal Fruit Monitoring via 3D Instance Segmentation and Re-Identification using Colored Point Clouds