University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Direct-from-Video: Unsupervised NRSfM

Lebeda, K, Hadfield, SJ and Bowden, R (2016) Direct-from-Video: Unsupervised NRSfM In: 2nd ECCV Workshop on Recovering 6D Object Pose Estimation, 2016-10-09, Amsterdam, Netherlands.

[img]
Preview
Text
nonrigid_r6d_2016.pdf - Author's Original
Available under License : See the attached licence file.

Download (2MB) | Preview
[img]
Preview
Text (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

In this work we describe a novel approach to online dense non-rigid structure from motion. The problem is reformulated, incorporating ideas from visual object tracking, to provide a more general and unified technique, with feedback between the reconstruction and point-tracking algorithms. The resulting algorithm overcomes the limitations of many conventional techniques, such as the need for a reference image/template or precomputed trajectories. The technique can also be applied in traditionally challenging scenarios, such as modelling objects with strong self-occlusions or from an extreme range of viewpoints. The proposed algorithm needs no offline pre-learning and does not assume the modelled object stays rigid at the beginning of the video sequence. Our experiments show that in traditional scenarios, the proposed method can achieve better accuracy than the current state of the art while using less supervision. Additionally we perform reconstructions in challenging new scenarios where state-of-the-art approaches break down and where our method improves performance by up to an order of magnitude.

Item Type: Conference or Workshop Item (Conference Paper)
Subjects : Electronic Engineering
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Lebeda, KUNSPECIFIEDUNSPECIFIED
Hadfield, SJUNSPECIFIEDUNSPECIFIED
Bowden, RUNSPECIFIEDUNSPECIFIED
Date : 9 October 2016
Identification Number : 10.1007/978-3-319-49409-8_50
Uncontrolled Keywords : Non-rigid SfM, Structure from Motion, Visual Tracking, Template-free, Gaussian Process
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 20 Dec 2016 11:57
Last Modified : 31 Oct 2017 18:59
URI: http://epubs.surrey.ac.uk/id/eprint/813061

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800