PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations
Rui She, Sijie Wang, Qiyu Kang, Kai Zhao, Yang Song, Wee Peng Tay, Tianyu Geng, Xingchao Jian
Abstract
Point cloud registration is a crucial technique in 3D computer vision with a wide range of applications. However, this task can be challenging, particularly in large fields of view with dynamic objects, environmental noise, or other perturbations. To address this challenge, we propose a model called PosDiffNet. Our approach performs hierarchical registration based on window-level, patch-level, and point-level correspondence. We leverage a graph neural partial differential equation (PDE) based on Beltrami flow to obtain high-dimensional features and position embeddings for point clouds. We incorporate position embeddings into a Transformer module based on a neural ordinary differential equation (ODE) to efficiently represent patches within points. We employ the multi-level correspondence derived from the high feature similarity scores to facilitate alignment between point clouds. Subsequently, we use registration methods such as SVD-based algorithms to predict the transformation using corresponding point pairs. We evaluate PosDiffNet on several 3D point cloud datasets, verifying that it achieves state-of-the-art (SOTA) performance for point cloud registration in large fields of view with perturbations. The implementation code of experiments is available at https://github.com/AI-IT-AVs/PosDiffNet.
BibTeX
@article{She_Wang_Kang_Zhao_Song_Tay_Geng_Jian_2024, title={PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/27775}, DOI={10.1609/aaai.v38i1.27775}, abstractNote={Point cloud registration is a crucial technique in 3D computer vision with a wide range of applications. However, this task can be challenging, particularly in large fields of view with dynamic objects, environmental noise, or other perturbations. To address this challenge, we propose a model called PosDiffNet. Our approach performs hierarchical registration based on window-level, patch-level, and point-level correspondence. We leverage a graph neural partial differential equation (PDE) based on Beltrami flow to obtain high-dimensional features and position embeddings for point clouds. We incorporate position embeddings into a Transformer module based on a neural ordinary differential equation (ODE) to efficiently represent patches within points. We employ the multi-level correspondence derived from the high feature similarity scores to facilitate alignment between point clouds. Subsequently, we use registration methods such as SVD-based algorithms to predict the transformation using corresponding point pairs. We evaluate PosDiffNet on several 3D point cloud datasets, verifying that it achieves state-of-the-art (SOTA) performance for point cloud registration in large fields of view with perturbations. The implementation code of experiments is available at https://github.com/AI-IT-AVs/PosDiffNet.}, number={1}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={She, Rui and Wang, Sijie and Kang, Qiyu and Zhao, Kai and Song, Yang and Tay, Wee Peng and Geng, Tianyu and Jian, Xingchao}, year={2024}, month={Mar.}, pages={231-239} }