Year: 2025
Type: article
Abstract: Point cloud rigid registration is a fundamental problem in 3D computer vision. In the multiview case, we aim to find a set of 6D poses to align a set of objects. Methods based on pairwise registration rely on a subsequent synchronization algorithm, which makes them poorly scalable with the number of views. Generative approaches overcome this limitation, but are based on Gaussian Mixture Models and use an Expectation-Maximization algorithm. Hence, they are not well suited to handle large transformations. Moreover, most existing methods cannot handle high levels of degradations. In this paper, we introduce POLAR (POint cloud LAtent Registration), a multiview registration method able to efficiently deal with a large number of views, while being robust to a high level of degradations and large initial angles. To achieve this, we transpose the registration problem into the latent space of a pretrained autoencoder, design a loss taking degradations into account, and develop an efficient multistart optimization strategy. Our proposed method significantly outperforms state-of-the-art approaches on synthetic and real data. POLAR is available at github.com/pypolar/polar or as a standalone package which can be installed with pip install polaregistration.
Authors: Luc Vedrenne, Sylvain Faisan, Denis Fortun
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
Awards: G164444715, Single particule reconstruction in fluorescence microscopy, Par-delà les frontières, l'Université de Strasbourg, G2255650664, G2694206344, Façonner les talents en formation et en recherche à l'Université de Strasbourg, G3357951378, G399734812, G471331628, G4779185514, G6136357505, G6276897512, G7240651115, G8395392860
OpenAlex ID: W4410114642