SECOND: Sparsely Embedded Convolutional Detection
Explore this paper's citation graph
Summary
An improved sparse convolution method for Voxel-based 3D convolutional networks is investigated, which significantly increases the speed of both training and inference and introduces a new form of angle loss regression to improve the orientation estimation performance.
- Type
- article
- Published
- 2018-10-01
- Cited by
- 3,657
- References
- 36
- Access
- Open access
- OpenAlex
- https://openalex.org/W2897529137
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:52957856
Keywords
Point cloud, Lidar, Computer science, Artificial intelligence, Inference
References
- Spatially-sparse convolutional neural networks
- You Only Look Once: Unified, Real-Time Object Detection
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Sparse 3D convolutional neural networks
- Are we ready for autonomous driving? The KITTI vision benchmark suite
- Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images
- Voting for Voting in Online Point Cloud Object Detection
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Monocular 3D Object Detection for Autonomous Driving
- 3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection
- Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks
- Multi-view 3D Object Detection Network for Autonomous Driving
- 3D fully convolutional network for vehicle detection in point cloud
- 3D Bounding Box Estimation Using Deep Learning and Geometry
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- Parallel Multi Channel convolution using General Matrix Multiplication
- Submanifold Sparse Convolutional Networks
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- Frustum PointNets for 3D Object Detection from RGB-D Data
- 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
Cited by
- Simulating LIDAR Point Cloud for Autonomous Driving using Real-world Scenes and Traffic Flows
- PointPillars: Fast Encoders for Object Detection From Point Clouds
- 3D Backbone Network for 3D Object Detection
- Augmented LiDAR Simulator for Autonomous Driving
- Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds
- Détection et localisation d'objets 3D par apprentissage profond en topologie capteur
- Monocular 3D Object Detection via Geometric Reasoning on Keypoints
- Cooper: Cooperative Perception for Connected Autonomous Vehicles Based on 3D Point Clouds
- Multimodal End-to-End Autonomous Driving
- SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization
- PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud
- Multi-Task Multi-Sensor Fusion for 3D Object Detection
- Attentional PointNet for 3D-Object Detection in Point Clouds
- Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss
- Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
- A Survey of Autonomous Driving: Common Practices and Emerging Technologies
- MCF3D: Multi-Stage Complementary Fusion for Multi-Sensor 3D Object Detection
- Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction
- Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds
- Vehicular Multi-object Tracking with Persistent Detector Failures
Related papers
- Evaluation of time-based ranging methods: Does the choice matter?
- Ranging Sensor Fusion in LISA Data Processing: Treatment of Ambiguities, Noise, and On-Board Delays in LISA Ranging Observables
- Performance Comparison of Asynchronous Ranging Algorithms
- Ranging-Aided Ground Robot Navigation Using UWB Nodes at Unknown Locations
- Performance Analysis of Ranging Techniques for the KPLO Mission
- A laser ranging method with high precision and large range in high speed based on phase measurement
- Embedded ranging system in ISM band
- On the Enhanced Ranging Performance for IEEE 802.15.4 Compliant WSN Devices