Deep Learning for 3D Point Cloud Understanding: A Survey
arXiv:2009.08920
Abstract
The development of practical applications, such as autonomous driving and robotics, has brought increasing attention to 3D point cloud understanding. While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unstructured and noisy 3D points. To demonstrate the latest progress of deep learning for 3D point cloud understanding, this paper summarizes recent remarkable research contributions in this area from several different directions (classification, segmentation, detection, tracking, flow estimation, registration, augmentation and completion), together with commonly used datasets, metrics and state-of-the-art performances. More information regarding this survey can be found at: https://github.com/SHI-Labs/3D-Point-Cloud-Learning.
References in corpus (12)
- Point-Set Registration: Coherent Point Drift
- RPM-Net: Robust Point Matching using Learned Features
- ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
- Deep Continuous Fusion for Multi-Sensor 3D Object Detection
- PCPNET: Learning Local Shape Properties from Raw Point Clouds
- Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud
- PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing
- PointRGCN: Graph Convolution Networks for 3D Vehicles Detection Refinement
- Probabilistic 3D Multi-Object Tracking for Autonomous Driving
- Tangent Convolutions for Dense Prediction in 3D
- Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels
- Point Cloud Instance Segmentation using Probabilistic Embeddings