Scholarlink

<p>This study presents PillarFocusNet, a novel network about 3D point cloud object detection that optimizes the PointPillars framework to improve detection performance. First, we propose the Pillar Clustering Sampling Method to address the sparse and uneven distribution of 3D point cloud data. Second, we introduce the Mixed Pooling Dilated Convolution Layer (MPDC layer) to enhance feature extraction. Finally, we integrate the Space-Channel Synergistic Enhancement Module (SCS-EM) to improve feature representation across both spatial and channel dimensions. Results from KITTI dataset experiments demonstrate that PillarFocusNet enhances bbox, bev, and 3d detection performance by 1.3%, 2.9%, and 3.4%, respectively, when compared to PointPillars. The code and models are publicly available at <a href="https://github.com/Gaoooyhan/PillarFocusNet">https://github.com/Gaoooyhan/PillarFocusNet</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PillarFocusNet for 3D object detection with perceptual diffusion and key feature understanding

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月13日

查看全文
  • Yuhan Gao,
  • Peng Wang,
  • Xiaoyan Li,
  • Bo Sun,
  • Mengyu Sun,
  • Liangliang Li,
  • Ruohai Di

摘要

This study presents PillarFocusNet, a novel network about 3D point cloud object detection that optimizes the PointPillars framework to improve detection performance. First, we propose the Pillar Clustering Sampling Method to address the sparse and uneven distribution of 3D point cloud data. Second, we introduce the Mixed Pooling Dilated Convolution Layer (MPDC layer) to enhance feature extraction. Finally, we integrate the Space-Channel Synergistic Enhancement Module (SCS-EM) to improve feature representation across both spatial and channel dimensions. Results from KITTI dataset experiments demonstrate that PillarFocusNet enhances bbox, bev, and 3d detection performance by 1.3%, 2.9%, and 3.4%, respectively, when compared to PointPillars. The code and models are publicly available at https://github.com/Gaoooyhan/PillarFocusNet.