Rotation Synchronization via Deep Matrix Factorization
- URL: http://arxiv.org/abs/2305.05268v1
- Date: Tue, 9 May 2023 08:46:05 GMT
- Title: Rotation Synchronization via Deep Matrix Factorization
- Authors: Gk Tejus, Giacomo Zara, Paolo Rota, Andrea Fusiello, Elisa Ricci,
Federica Arrigoni
- Abstract summary: We focus on the formulation of rotation synchronization via neural networks.
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.
- Score: 24.153207403324917
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Rotation Averaging: A Primal-Dual Method and Closed-Forms in Cycle Graphs [6.511636092857915]
A benchmark of geometric reconstruction, averaging seeks the set of absolute settings that optimally explains a set of measured relative orientations between them.
We propose a novel primal-dual cycle method motivated by the widely accepted spectral theory.
arXiv Detail & Related papers (2024-05-29T21:46:39Z) - Intensity Profile Projection: A Framework for Continuous-Time
Representation Learning for Dynamic Networks [50.2033914945157]
We present a representation learning framework, Intensity Profile Projection, for continuous-time dynamic network data.
The framework consists of three stages: estimating pairwise intensity functions, learning a projection which minimises a notion of intensity reconstruction error.
Moreoever, we develop estimation theory providing tight control on the error of any estimated trajectory, indicating that the representations could even be used in quite noise-sensitive follow-on analyses.
arXiv Detail & Related papers (2023-06-09T15:38:25Z) - ReSync: Riemannian Subgradient-based Robust Rotation Synchronization [26.151024152071784]
This work presents ReSync, a subgradient-based algorithm for solving the robust synchronization problem.
Results demonstrate the effectiveness of ReSync under appropriate conditions.
arXiv Detail & Related papers (2023-05-24T13:31:11Z) - Temporally-Consistent Surface Reconstruction using Metrically-Consistent
Atlases [131.50372468579067]
We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds.
We represent the reconstructed surfaces as atlases computed by a neural network, which enables us to establish correspondences between frames.
Our approach outperforms state-of-the-art ones on several challenging datasets.
arXiv Detail & Related papers (2021-11-12T17:48:25Z) - Learning Iterative Robust Transformation Synchronization [71.73273007900717]
We propose to use graph neural networks (GNNs) to learn transformation synchronization.
In this work, we avoid handcrafting robust loss functions, and propose to use graph neural networks (GNNs) to learn transformation synchronization.
arXiv Detail & Related papers (2021-11-01T07:03:14Z) - Utilizing synchronization to partition power networks into microgrids [1.224954637705144]
partitioning a power grid into a set of microgrids, or islands, is of interest for both the design of future smart grids and as a last resort to restore power dispatchment in sections of a grid affected by an extreme failure.
In this paper, we take a different route and obtain the grid partition by exploiting the synchronization dynamics of a cyberlayer of Kuramoto oscillators.
arXiv Detail & Related papers (2021-07-26T12:32:11Z) - Joint Community Detection and Rotational Synchronization via
Semidefinite Programming [17.845257705485533]
In the presence of heterogeneous data, where randomly rotated objects fall into multiple underlying categories, it is challenging to simultaneously classify them into clusters and synchronize them based on pairwise relations.
We propose a series of semidefinite relaxations, and prove their exact recovery when extending the celebrated block model to this new setting.
Numerical experiments demonstrate the efficacy of our proposed algorithms and confirm our theoretical result which indicates a sharp phase transition for exact recovery.
arXiv Detail & Related papers (2021-05-13T01:40:20Z) - On the Robustness of Multi-View Rotation Averaging [77.09542018140823]
We introduce the $epsilon$-cycle consistency term into the solver.
We implicitly constrain the negative effect of erroneous measurements by weight reducing.
Experiment results demonstrate that our proposed approach outperforms state of the arts on various benchmarks.
arXiv Detail & Related papers (2021-02-09T05:47:37Z) - MotioNet: 3D Human Motion Reconstruction from Monocular Video with
Skeleton Consistency [72.82534577726334]
We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video.
Our method is the first data-driven approach that directly outputs a kinematic skeleton, which is a complete, commonly used, motion representation.
arXiv Detail & Related papers (2020-06-22T08:50:09Z) - Revisiting Initialization of Neural Networks [72.24615341588846]
We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix.
Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
arXiv Detail & Related papers (2020-04-20T18:12:56Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.