PG: Pacific Graphics Short Papers

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/995

Browse

Browsing PG: Pacific Graphics Short Papers by Subject "3D object detection"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    PVP-SSD: Point-Voxel Fusion with Partitioned Point Cloud Sampling for Anchor-Free Single-Stage Small 3D Object Detection
    (The Eurographics Association, 2024) Wu, Xinlin; Tian, Yibin; Pan, Yin; Zhang, Zhiyuan; Wu, Xuesong; Wang, Ruisheng; Zeng, Zhi; Chen, Renjie; Ritschel, Tobias; Whiting, Emily
    Single-stage object detection from 3D point clouds in autonomous driving faces significant challenges, particularly in accurately detecting small objects. To address this issue, we propose a novel method called Point-Voxel dual-branch feature extraction with Partitioned point cloud sampling for anchor-free Single-Stage Detection of 3D objects (PVP-SSD). The network comprises two branches: a point branch and a voxel branch. In the point branch, a partitioned point cloud sampling strategy leverages axial features to divide the point cloud. Then, it assigns different sampling weights to various segments to enhance the sampling accuracy. Additionally, a local feature enhancement module explicitly calculates the correlation between key points and query points, improving the extraction of local features. In the voxel branch, we use 3D sparse convolution to extract instance structural features efficiently. The point-voxel dual-branch fusion dynamically integrates instance features extracted from both branches using a self-attention mechanism, which contains not only the category information of the detected object but also the spatial dimensions and heading angle. Consequently, PVP-SSD achieves a certain balance between preserving detailed information and maintaining structural integrity. Experimental results on the KITTI and ONCE datasets demonstrate that PVP-SSD excels in multi-category small 3D object detection.