PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing
Explore this paper's citation graph
Summary
Experimental results show that PointRNN, PointGRU and PointLSTM are able to produce correct predictions on both synthetic and real-world datasets, demonstrating their ability to model point cloud sequences.
- Type
- preprint
- Published
- 2019-10-18
- Cited by
- 113
- References
- 37
- Access
- Open access
- OpenAlex
- https://openalex.org/W2980815547
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:204788858
Keywords
Point cloud, Point (geometry), State (computer science), Point-to-point, Combinatorics
References
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- Long Short-Term Memory
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
- Multi-view 3D Object Detection Network for Autonomous Driving
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
- Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction
- Learning Representations and Generative Models for 3D Point Clouds
- PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
- Frustum PointNets for 3D Object Detection from RGB-D Data
- 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
- SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
- SPLATNet: Sparse Lattice Networks for Point Cloud Processing
- SO-Net: Self-Organizing Network for Point Cloud Analysis
- PointPillars: Fast Encoders for Object Detection From Point Clouds
- Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network
- Associatively Segmenting Instances and Semantics in Point Clouds
Cited by
- nuScenes: A Multimodal Dataset for Autonomous Driving
- Sequential Forecasting of 100,000 Points
- Unsupervised Sequence Forecasting of 100,000 Points for Unsupervised Trajectory Forecasting
- An Efficient PointLSTM for Point Clouds Based Gesture Recognition
- Deep Learning for 3D Point Clouds: A Survey
- An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds
- From Video Classification to Video Prediction: Deep Learning Approaches to Video Modelling
- Deep Learning for 3D Point Cloud Understanding: A Survey
- A Novel Object Re-Track Framework for 3D Point Clouds
- Human Segmentation with Dynamic LiDAR Data
- RAFT-3D: Scene Flow using Rigid-Motion Embeddings
- Radar Artifact Labeling Framework (RALF): Method for Plausible Radar Detections in Datasets
- MoNet: Motion-Based Point Cloud Prediction Network
- Temporal LiDAR Frame Prediction for Autonomous Driving
- Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion
- PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
- Moving Object Detection by 3D Flow Field Analysis
- Spatio-Temporal Graph-RNN for Point Cloud Prediction
- Unsupervised Visual Representation Learning via Dual-Level Progressive Similar Instance Selection
- Scalable Scene Flow From Point Clouds in the Real World
Related papers
- Point to Point Communications Based on WinSock in the Local Area Network
- To realize the communication from point to point by the winsock activeX
- Implementation Point-to-Point Communication between DSPs by SPI
- Analysis of Point-to-Point versus Hub-and-Spoke airline networks
- An Analysis on Positional Accuracy of Urban Control Point for Connecting to Supplementary Control Point
- The Method of Making Perspective View on Small Drawing-board
- Summaries on supporting papers on “Long-distance point-to-point communication”
- Impact and Limitations of Point-to-Point Performance on Collective Algorithms
- Travel time models for a three-dimensional compact AS/RS considering different I/O point policies