STD: Sparse-to-Dense 3D Object Detector for Point Cloud

Abstract

We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD). The first stage is a bottom-up proposal generation network that uses raw point cloud as input to generate accurate proposals by seeding each point with a new spherical anchor. It achieves a high recall with less computation compared with prior works. Then, PointsPool is applied for generating proposal features by transforming their interior point features from sparse expression to compact representation, which saves even more computation time. In box prediction, which is the second stage, we implement a parallel intersection-over-union (IoU) branch to increase awareness of localization accuracy, resulting in further improved performance. We conduct experiments on KITTI dataset, and evaluate our method in terms of 3D object and Bird's Eye View (BEV) detection. Our method outperforms other state-of-the-arts by a large margin, especially on the hard set, with inference speed more than 10 FPS.

arXiv admin note: text overlap with arXiv:1812.05276

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
• PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation
• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
• Joint 3D Proposal Generation and Object Detection from View Aggregation
• SO-Net: Self-Organizing Network for Point Cloud Analysis

Cited by in corpus (23)

• Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
• PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
• Center-based 3D Object Detection and Tracking
• Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data
• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
• SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
• DSGN: Deep Stereo Geometry Network for 3D Object Detection
• Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
• Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
• LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention
• SESS: Self-Ensembling Semi-Supervised 3D Object Detection
• Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection
• SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
• DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution
• S-AT GCN: Spatial-Attention Graph Convolution Network based Feature Enhancement for 3D Object Detection
• MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views
• Weakly Supervised 3D Object Detection from Point Clouds
• ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
• 3D-MAN: 3D Multi-frame Attention Network for Object Detection
• Stereo RGB and Deeper LIDAR Based Network for 3D Object Detection
• PointNet on FPGA for Real-Time LiDAR Point Cloud Processing
• Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds
• DV-Det: Efficient 3D Point Cloud Object Detection with Dynamic Voxelization