Scene Flow Prior Based Point Cloud Completion with Masked Transformer (Student Abstract)

Junzhe Ding, Yufei Que, Jin Zhang, Cheng Wu

AAAI 2024 pp. 23473-23474

doi:10.1609/AAAI.V38I21.30434 /aaai/2024/ding2024aaai-scene/

Abstract

It is necessary to explore an effective point cloud completion mechanism that is of great significance for real-world tasks such as autonomous driving, robotics applications, and multi-target tracking. In this paper, we propose a point cloud completion method using a self-supervised transformer model based on the contextual constraints of scene flow. Our method uses the multi-frame point cloud context relationship as a guide to generate a series of token proposals, this priori condition ensures the stability of the point cloud completion. The experimental results show that the method proposed in this paper achieves high accuracy and good stability.

PDF AAAI Semantic Scholar

Cite

Text

Ding et al. "Scene Flow Prior Based Point Cloud Completion with Masked Transformer (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30434

Markdown

[Ding et al. "Scene Flow Prior Based Point Cloud Completion with Masked Transformer (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/ding2024aaai-scene/) doi:10.1609/AAAI.V38I21.30434

BibTeX

@inproceedings{ding2024aaai-scene,
  title     = {{Scene Flow Prior Based Point Cloud Completion with Masked Transformer (Student Abstract)}},
  author    = {Ding, Junzhe and Que, Yufei and Zhang, Jin and Wu, Cheng},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23473-23474},
  doi       = {10.1609/AAAI.V38I21.30434},
  url       = {https://mlanthology.org/aaai/2024/ding2024aaai-scene/}
}