A Solution for Multi-Alignment by Transformation Synchronisation

10/30/2014
by   Florian Bernard, et al.
0

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.

READ FULL TEXT
research
01/27/2019

Learning Transformation Synchronization

Reconstructing the 3D model of a physical object typically requires us t...
research
04/08/2020

A Robust Method for Image Stitching

We propose a novel method for image stitching that is robust against rep...
research
06/25/2018

Towards Optimal Transport with Global Invariances

Many problems in machine learning involve calculating correspondences be...
research
12/04/2021

Dual-Flow Transformation Network for Deformable Image Registration with Region Consistency Constraint

Deformable image registration is able to achieve fast and accurate align...
research
05/23/2020

ProAlignNet : Unsupervised Learning for Progressively Aligning Noisy Contours

Contour shape alignment is a fundamental but challenging problem in comp...
research
03/13/2020

Joint Alignment From Pairwise Differences with a Noisy Oracle

In this work we consider the problem of recovering n discrete random var...
research
11/20/2017

Recover Missing Sensor Data with Iterative Imputing Network

Sensor data has been playing an important role in machine learning tasks...

Please sign up or login with your details

Forgot password? Click here to reset