PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer
arXiv:2404.14034 · doi:10.1109/TGRS.2024.3351286
Abstract
Point cloud registration is a fundamental technique in 3-D computer vision with applications in graphics, autonomous driving, and robotics. However, registration tasks under challenging conditions, under which noise or perturbations are prevalent, can be difficult. We propose a robust point cloud registration approach that leverages graph neural partial differential equations (PDEs) and heat kernel signatures. Our method first uses graph neural PDE modules to extract high dimensional features from point clouds by aggregating information from the 3-D point neighborhood, thereby enhancing the robustness of the feature representations. Then, we incorporate heat kernel signatures into an attention mechanism to efficiently obtain corresponding keypoints. Finally, a singular value decomposition (SVD) module with learnable weights is used to predict the transformation between two point clouds. Empirical experiments on a 3-D point cloud dataset demonstrate that our approach not only achieves state-of-the-art performance for point cloud registration but also exhibits better robustness to additive noise or 3-D shape perturbations.
Accepted by IEEE Transactions on Geoscience and Remote Sensing
References in corpus (9)
- PCT: Point cloud transformer
- Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
- DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration
- Learning general and distinctive 3D local deep descriptors for point cloud registration
- LassoNet: Deep Lasso-Selection of 3D Point Clouds
- Learning a Task-specific Descriptor for Robust Matching of 3D Point Clouds
- Structural Pruning for Diffusion Models
- RobustMat: Neural Diffusion for Street Landmark Patch Matching under Challenging Environments
- Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach