Scalable 3D Registration via Truncated Entry-wise Absolute Residuals

arXiv:2404.00915v1 Announce Type: new
Abstract: Given an input set of $3$D point pairs, the goal of outlier-robust $3$D registration is to compute some rotation and translation that align as many point pairs as possible. This is an important problem in computer vision, for which many highly accurate approaches have been recently proposed. Despite their impressive performance, these approaches lack scalability, often overflowing the $16$GB of memory of a standard laptop to handle roughly $30,000$ point pairs. In this paper, we …

abstract arxiv compute computer computer vision cs.cv cs.ro outlier registration robust rotation scalable set translation type via vision wise