In this paper we address the rotation synchronization problem, where the objective is to recover absolute rotations starting from pairwise ones, where the unknowns and the measures are represented as nodes and edges of a graph, respectively. This problem is an essential task for structure from motion and simultaneous localization and mapping. We focus on the formulation of synchronization via neural networks, which has only recently begun to be explored in the literature. Inspired by deep matrix completion, we express rotation synchronization in terms of matrix factorization with a deep neural network. Our formulation exhibits implicit regularization properties and, more importantly, is unsupervised, whereas previous deep approaches are supervised. Our experiments show that we achieve comparable accuracy to the closest competitors in most scenes, while working under weaker assumptions.
Rotation Synchronization via Deep Matrix Factorization
Gk Tejus,Giacomo Zara,Paolo Rota,Andrea Fusiello,Elisa Ricci,F. Arrigoni
Published 2023 in IEEE International Conference on Robotics and Automation
ABSTRACT
PUBLICATION RECORD
- Publication year
2023
- Venue
IEEE International Conference on Robotics and Automation
- Publication date
2023-05-09
- Fields of study
Computer Science
- Identifiers
- External record
- Source metadata
Semantic Scholar
CITATION MAP
EXTRACTION MAP
CLAIMS
- No claims are published for this paper.
CONCEPTS
- No concepts are published for this paper.
REFERENCES
Showing 1-43 of 43 references · Page 1 of 1
CITED BY
Showing 1-10 of 10 citing papers · Page 1 of 1