PSA-Det3D: Pillar Set Abstraction for 3D object Detection
Not on the map. Why?
Abstract (arXiv)
Small object detection for 3D point cloud is a challenging problem because of two limitations: (1) Perceiving small objects is much more diffcult than normal objects due to the lack of valid points. (2) Small objects are easily blocked which breaks the shape of their meshes in 3D point cloud. In this paper, we propose a pillar set abstraction (PSA) and foreground point compensation (FPC) and design a point-based detection network, PSA-Det3D, to improve the detection performance for small object. The PSA embeds a pillar query operation on the basis of set abstraction (SA) to expand its receptive field of the network, which can aggregate point-wise features effectively. To locate more occluded objects, we persent a proposal generation layer consisting of a foreground point segmentation and a FPC module. Both the foreground points and the estimated centers are finally fused together to generate the detection result. The experiments on the KITTI 3D detection benchmark show that our proposed PSA-Det3D outperforms other algorithms with high accuracy for small object detection.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 20 Oct 2022.
Builds on
29 of 40 references.
References · 29
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
- 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
- 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
- 2020Center-based 3D Object Detection and Trackingcited by 1,143
- 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
- 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
- 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
- 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
- 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
- 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
17 more
- 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
- 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
- 20203D Object Detection with Pointformercited by 194
- 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
- 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
- 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
- 2019Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detectioncited by 124
- 2019Fast Point R-CNNcited by 119
- 2019TANet: Robust 3D Object Detection from Point Clouds with Triple Attentioncited by 108
- 2020Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Reviewcited by 107
- 2019Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspotscited by 84
- 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
- 2021M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformerscited by 74
- 2022SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detectioncited by 52
- 2022DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detectioncited by 25
- 2021BADet: Boundary-Aware 3D Object Detection from Point Cloudscited by 17
- 2021Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar Networkcited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.