Scholarlink

<p>In this paper, a two-stage light detection and ranging (LiDAR) three-dimensional (3D) object detection framework is presented, namely point-voxel dual transformer (PV-DT3D), which is a transformer-based method. In the proposed PV-DT3D, point-voxel fusion features are used for proposal refinement. Specifically, keypoints are sampled from entire point cloud scene and used to encode representative scene features via a proposal-aware voxel set abstraction module. Subsequently, following the generation of proposals by the region proposal networks (RPN), the internal encoded keypoints are fed into the dual transformer encoder-decoder architecture. In 3D object detection, the proposed PV-DT3D takes advantage of both point-wise transformer and channel-wise architecture to capture contextual information from the spatial and channel dimensions. Experiments conducted on the highly competitive KITTI 3D car detection leaderboard show that the PV-DT3D achieves superior detection accuracy among state-of-the-art point-voxel-based methods.</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

Point-voxel dual transformer for LiDAR 3D object detection

  • 期刊论文

  • 发表日期：

    2025年8月27日

查看全文
  • Jigang Tong,
  • Fanhang Yang,
  • Sen Yang,
  • Shengzhi Du

摘要

In this paper, a two-stage light detection and ranging (LiDAR) three-dimensional (3D) object detection framework is presented, namely point-voxel dual transformer (PV-DT3D), which is a transformer-based method. In the proposed PV-DT3D, point-voxel fusion features are used for proposal refinement. Specifically, keypoints are sampled from entire point cloud scene and used to encode representative scene features via a proposal-aware voxel set abstraction module. Subsequently, following the generation of proposals by the region proposal networks (RPN), the internal encoded keypoints are fed into the dual transformer encoder-decoder architecture. In 3D object detection, the proposed PV-DT3D takes advantage of both point-wise transformer and channel-wise architecture to capture contextual information from the spatial and channel dimensions. Experiments conducted on the highly competitive KITTI 3D car detection leaderboard show that the PV-DT3D achieves superior detection accuracy among state-of-the-art point-voxel-based methods.