A Solution for Multi-Alignment by Transformation Synchronisation
arXiv:1410.8546 · doi:10.1109/CVPR.2015.7298828
Abstract
The alignment of a set of objects by means of transformations plays an important role in computer vision. Whilst the case for only two objects can be solved globally, when multiple objects are considered usually iterative methods are used. In practice the iterative methods perform well if the relative transformations between any pair of objects are free of noise. However, if only noisy relative transformations are available (e.g. due to missing data or wrong correspondences) the iterative methods may fail. Based on the observation that the underlying noise-free transformations can be retrieved from the null space of a matrix that can directly be obtained from pairwise alignments, this paper presents a novel method for the synchronisation of pairwise transformations such that they are transitively consistent. Simulations demonstrate that for noisy transformations, a large proportion of missing data and even for wrong correspondence assignments the method delivers encouraging results.
Accepted for CVPR 2015 (please cite CVPR version)
Cited by in corpus (15)
- Robust Rotation Synchronization via Low-rank and Sparse Matrix Decomposition
- Probabilistic Permutation Synchronization using the Riemannian Structure of the Birkhoff Polytope
- Synchronisation of Partial Multi-Matchings via Non-negative Factorisations
- Distributed methods for synchronization of orthogonal matrices over graphs
- Learning to Communicate and Correct Pose Errors
- MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
- Multiview Point Cloud Registration via Optimization in an Autoencoder Latent Space
- Learning Transformation Synchronization
- Sparse Quadratic Optimisation over the Stiefel Manifold with Application to Permutation Synchronisation
- Non-Negative Spherical Relaxations for Universe-Free Multi-Matching and Clustering
- i3DMM: Deep Implicit 3D Morphable Model of Human Heads
- Isometric Multi-Shape Matching
- cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey
- cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey
- Least-squares registration of point sets over SE (d) using closed-form projections