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
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver