基于 Surfel 的等变 SE(3) 特征三维配准
Surfel-based 3D Registration with Equivariant SE(3) Features
AI总结：
提出一种基于 surfel 的位姿回归方法，利用虚拟相机初始化 surfel 并学习显式 SE(3) 等变特征，结合交叉注意力与 Huber 损失实现稳健点云配准。
摘要：
点云配准对于在遥感或数字遗产的三维重建中确保多个局部点云的三维对齐一致性至关重要。尽管目前存在多种基于点云的配准方法，包括非学习方法和基于学习的方法，但它们都忽略了点方向和点不确定性，使模型容易受到噪声输入以及输入点云剧烈旋转（如正交变换）的影响；因此，需要借助变换增强来获得大量训练点云。为解决这些问题，我们提出了一种新颖的基于 surfel 的位姿学习回归方法。该方法可利用虚拟透视相机参数从激光雷达点云初始化 surfels，并通过 SE(3) 等变卷积核学习同时包含位置和旋转的显式 SE(3) 等变特征，以预测源扫描与目标扫描之间的相对变换。模型由等变卷积编码器、用于相似度计算的交叉注意力机制、全连接解码器和非线性 Huber 损失组成。在室内和室外数据集上的实验结果表明，与最先进方法相比，我们的模型在真实点云扫描上具有优越性和稳健性能。
英文摘要：
Point cloud registration is crucial for ensuring 3D alignment consistency of multiple local point clouds in 3D reconstruction for remote sensing or digital heritage. While various point cloud-based registration methods exist, both non-learning and learning-based, they ignore point orientations and point uncertainties, making the model susceptible to noisy input and aggressive rotations of the input point cloud like orthogonal transformation; thus, it necessitates extensive training point clouds with transformation augmentations. To address these issues, we propose a novel surfel-based pose learning regression approach. Our method can initialize surfels from Lidar point cloud using virtual perspective camera parameters, and learns explicit $\mathbf{SE(3)}$ equivariant features, including both position and rotation through $\mathbf{SE(3)}$ equivariant convolutional kernels to predict relative transformation between source and target scans. The model comprises an equivariant convolutional encoder, a cross-attention mechanism for similarity computation, a fully-connected decoder, and a non-linear Huber loss. Experimental results on indoor and outdoor datasets demonstrate our model superiority and robust performance on real point-cloud scans compared to state-of-the-art methods.
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。
