PointDifformer：基于神经扩散和Transformer的鲁棒点云配准
PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer
AI总结：
提出一种基于图神经偏微分方程和热核签名的鲁棒点云配准方法，通过增强特征表示和高效获取关键点，结合可学习SVD模块预测变换，在噪声和扰动条件下实现了最先进性能。
摘要：
点云配准是3-D计算机视觉中的一项基础技术，广泛应用于图形学、自动驾驶和机器人领域。然而，在噪声或扰动普遍存在的挑战性条件下，配准任务可能很困难。我们提出了一种鲁棒的点云配准方法，该方法利用图神经偏微分方程（PDEs）和热核签名。我们的方法首先使用图神经PDE模块，通过聚合来自3-D点邻域的信息，从点云中提取高维特征，从而增强特征表示的鲁棒性。然后，我们将热核签名纳入注意力机制，以高效地获取对应关键点。最后，使用一个具有可学习权重的奇异值分解（SVD）模块来预测两个点云之间的变换。在3-D点云数据集上的实验表明，我们的方法不仅实现了点云配准的最先进性能，而且对加性噪声或3-D形状扰动表现出更好的鲁棒性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
