Event Details
A Comparative Analysis of Point Sampling Strategies in Point-based 3D Object Detection
Presenter: Rui Zhu
Supervisor:
Date: Fri, November 24, 2023
Time: 11:00:00 - 00:00:00
Place: ZOOM - Please see below.
ABSTRACT
Zoom Meeting Link:
Meeting ID: 891 5447 1525
Password: 453213
One tap mobile
+17789072071,,89154471525# Canada
+16475580588,,89154471525# Canada
Dial by your location
+1 778 907 2071 Canada
+1 647 558 0588 Canada
Note: Please log in to Zoom via SSO and your UVic Netlink ID
ABSTRACT
Point-based 3D object detection has been receiving increasing attention as it can preserve the geometric information of a point cloud and avoid quantization errors or information loss caused by voxelization or projection. Point sampling plays an important role in point-based 3D detectors yet has not been thoroughly explored. In our research, we conduct a comparative analysis of three point sampling strategies to gain a deep understanding of the effect that each strategy imposes on the final performance and intermediate stages of the network. We introduce density-aware sampling and semantic-aware sampling strategies and fit them into the backbone of a lightweight and effective baseline model, aiming to reduce the density imbalance of the point cloud and better utilize semantic information. The density-aware strategy effectively balances the density but the inference time is not suitable for real-time application. Semantic-aware sampling biased on foreground points achieves a 0.19\% improvement over the baseline. Analysis on statistics and visualization reveals future research direction. We build our models on the MMDetection3D platform and evaluate performance on the KITTI dataset.