Surfel-based 3D Registration with Equivariant SE(3) Features
By: Xueyang Kang , Hang Zhao , Kourosh Khoshelham and more
Potential Business Impact:
Aligns 3D scans better, even when tilted.
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.
Similar Papers
Intraoperative 2D/3D Registration via Spherical Similarity Learning and Inference-Time Differentiable Levenberg-Marquardt Optimization
CV and Pattern Recognition
Helps surgeons see inside patients better during operations.
Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection
CV and Pattern Recognition
Finds tiny flaws in 3D shapes, even when tilted.
Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
CV and Pattern Recognition
Makes 3D scans match perfectly, even with bad data.