|国家预印本平台
首页|Surfel-based 3D Registration with Equivariant SE(3) Features

Surfel-based 3D Registration with Equivariant SE(3) Features

Surfel-based 3D Registration with Equivariant SE(3) Features

来源:Arxiv_logoArxiv
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.

Xueyang Kang、Hang Zhao、Kourosh Khoshelham、Patrick Vandewalle

遥感技术

Xueyang Kang,Hang Zhao,Kourosh Khoshelham,Patrick Vandewalle.Surfel-based 3D Registration with Equivariant SE(3) Features[EB/OL].(2025-08-28)[2025-09-03].https://arxiv.org/abs/2508.20789.点此复制

评论