跳到主要导航 跳到搜索 跳到主要内容

Self-Supervised 3D Point Cloud Detection with Depthwise Separable Masked Autoencoders

  • Jiayi Zhou
  • , Yaqian Ning
  • , Jie Cao*
  • , Zhaoyang Li
  • , Pengcheng Ji
  • , Sirui Guo
  • *此作品的通讯作者
  • Beijing Institute of Technology
  • Changchun University of Science and Technology

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

Three-dimensional object detection from LiDAR point clouds is essential for autonomous driving, yet existing methods typically rely on costly and extensively annotated datasets. Self-supervised masked autoencoders (MAE) provide a promising alternative, but effectively capturing local geometric structures while maintaining computational efficiency remains challenging. This paper presents DS-MAE, a depthwise separable masked autoencoder for self-supervised 3D point cloud detection. DS-MAE introduces a pyramidal transformer encoder with depthwise separable attention to enhance local geometric feature extraction while reducing computational cost. A depthwise separable generative decoder is further designed for multi-scale masked feature reconstruction, while a density-aware reconstruction loss accounts for the non-uniform point density of LiDAR observations. Experiments on the KITTI, Waymo Open Dataset (WOD), and a small-scale subset of the ONCE dataset demonstrate the effectiveness of DS-MAE, achieving 67.95%, 67.70%, and 58.92% mAP, respectively. On WOD, the reported performance is achieved using only 20% of the labeled training data, demonstrating the effectiveness of DS-MAE under limited supervision.

源语言英语
期刊论文编号3148
期刊Remote Sensing
卷18
期18
DOI
出版状态已出版 - 9月 2026
已对外发布是

学术指纹

探究 'Self-Supervised 3D Point Cloud Detection with Depthwise Separable Masked Autoencoders' 的科研主题。它们共同构成独一无二的学术指纹。

引用此