EUVIMEDEUVIMED entdecken
Crossref

Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation

Xiaoqi An, Lin Zhao, Chen Gong, Jun Li, Jian Yang

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (2) · 1755-1763

DOI: 10.1609/aaai.v39i2.32169 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Xiaoqi An und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of autonomous driving, LiDAR-based 3D Human Pose Estimation (3D HPE) is becoming a research focus. However, due to the noise and sparsity of LiDAR-captured point clouds, robust human pose estimation remains challenging. Most of the existing methods use temporal information, multi-modal fusion, or SMPL optimization to correct biased results. In this work, we try to obtain sufficient information for 3D HPE only by modeling the intrinsic properties of low-quality point clouds. Hence, a simple yet powerful method is proposed, which provides insights both on modeling and augmentation of point clouds. Specifically, we first propose a concise and effective density-aware pose transformer (DAPT) to get stable keypoint representations. By using a set of joint anchors and a carefully designed exchange module, valid information is extracted from point clouds with different densities. Then 1D heatmaps are utilized to represent the precise locations of the keypoints. Secondly, a comprehensive LiDAR human synthesis and augmentation method is proposed to pre-train the model, enabling it to acquire a better human body prior. We increase the diversity of point clouds by randomly sampling human positions and orientations and by simulating occlusions through the addition of laser-level masks. Extensive experiments have been conducted on multiple datasets, including IMU-annotated LidarHuman26M, SLOPER4D, and manually annotated Waymo Open Dataset v2.0 (Waymo), HumanM3. Our method demonstrates SOTA performance in all scenarios. In particular, compared with LPFormer on Waymo, we reduce the average MPJPE by 10.0mm. Compared with PRN on SLOPER4D, we notably reduce the average MPJPE by 20.7mm.

Zitieren

APA

An, X., Zhao, L., Gong, C., Li, J., & Yang, J. (2025). Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(2), 1755-1763. https://doi.org/10.1609/aaai.v39i2.32169

Vancouver

An X, Zhao L, Gong C, Li J, Yang J. Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(2):1755-1763. doi:10.1609/aaai.v39i2.32169

BibTeX
@article{An2025,
  author = {An, Xiaoqi and Zhao, Lin and Gong, Chen and Li, Jun and Yang, Jian},
  title = {Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {2},
  pages = {1755--1763},
  doi = {10.1609/aaai.v39i2.32169}
}
Kostenlos starten →