3DSSD: Point-based 3D Single Stage Object Detector

Abstract

Currently, there have been many kinds of voxel-based 3D single stage detectors, while point-based single stage methods are still underexplored. In this paper, we first present a lightweight and effective point-based 3D single stage object detector, named 3DSSD, achieving a good balance between accuracy and efficiency. In this paradigm, all upsampling layers and refinement stage, which are indispensable in all existing point-based methods, are abandoned to reduce the large computation cost. We novelly propose a fusion sampling strategy in downsampling process to make detection on less representative points feasible. A delicate box prediction network including a candidate generation layer, an anchor-free regression head with a 3D center-ness assignment strategy is designed to meet with our demand of accuracy and speed. Our paradigm is an elegant single stage anchor-free framework, showing great superiority to other existing methods. We evaluate 3DSSD on widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well, with inference speed more than 25 FPS, 2x faster than former state-of-the-art point-based methods.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
• Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
• Joint 3D Proposal Generation and Object Detection from View Aggregation
• IPOD: Intensive Point-based Object Detector for Point Cloud
• From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network
• Multi-View 3D Object Detection Network for Autonomous Driving
• Patch Refinement -- Localized 3D Object Detection
• 3D Fully Convolutional Network for Vehicle Detection in Point Cloud
• Multi-Task Multi-Sensor Fusion for 3D Object Detection

Cited by in corpus (14)

• Real-time 3D Single Object Tracking with Transformer
• CenterNet3D: An Anchor Free Object Detector for Point Cloud
• VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection
• CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud
• Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation
• LiDAR Spoofing Meets the New-Gen: Capability Improvements, Broken Assumptions, and New Attack Strategies
• An Efficient Hypergraph Approach to Robust Point Cloud Resampling
• Evaluating the Impact of Semantic Segmentation and Pose Estimation on Dense Semantic SLAM
• STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learning
• MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detection
• Dynamic Edge Weights in Graph Neural Networks for 3D Object Detection
• Voxel Transformer for 3D Object Detection
• TwistSLAM++: Fusing multiple modalities for accurate dynamic semantic SLAM
• RoIFusion: 3D Object Detection from LiDAR and Vision