The University of Southampton
University of Southampton Institutional Repository

Temporally coherent 4D reconstruction of complex dynamic scenes

Temporally coherent 4D reconstruction of complex dynamic scenes
Temporally coherent 4D reconstruction of complex dynamic scenes
This paper presents an approach for reconstruction of 4D temporally coherent models of complex dynamic scenes. No prior knowledge is required of scene structure or camera calibration allowing reconstruction from multiple moving cameras. Sparse-to-dense temporal correspondence is integrated with joint multi-view segmentation and reconstruction to obtain a complete 4D representation of static and dynamic objects. Temporal coherence is exploited to overcome visual ambiguities resulting in improved reconstruction of complex scenes. Robust joint segmentation and reconstruction of dynamic objects is achieved by introducing a geodesic star convexity constraint. Comparative evaluation is performed on a variety of unstructured indoor and outdoor dynamic scenes with hand-held cameras and multiple people. This demonstrates reconstruction of complete temporally coherent 4D scene models with improved nonrigid object segmentation and shape reconstruction.
1063-6919
4660-4669
IEEE
Mustafa, Armin
29037014-ab45-4368-81e3-6b698e9bbbd0
Kim, Hansung
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Guillemaut, Jean-Yves
fcaefbd8-8ba1-4c43-978c-0b5d432a3285
Hilton, Adrian
12782a55-4c4d-4dfb-a690-62505f6665db
Mustafa, Armin
29037014-ab45-4368-81e3-6b698e9bbbd0
Kim, Hansung
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Guillemaut, Jean-Yves
fcaefbd8-8ba1-4c43-978c-0b5d432a3285
Hilton, Adrian
12782a55-4c4d-4dfb-a690-62505f6665db

Mustafa, Armin, Kim, Hansung, Guillemaut, Jean-Yves and Hilton, Adrian (2016) Temporally coherent 4D reconstruction of complex dynamic scenes. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. pp. 4660-4669 . (doi:10.1109/CVPR.2016.504).

Record type: Conference or Workshop Item (Paper)

Abstract

This paper presents an approach for reconstruction of 4D temporally coherent models of complex dynamic scenes. No prior knowledge is required of scene structure or camera calibration allowing reconstruction from multiple moving cameras. Sparse-to-dense temporal correspondence is integrated with joint multi-view segmentation and reconstruction to obtain a complete 4D representation of static and dynamic objects. Temporal coherence is exploited to overcome visual ambiguities resulting in improved reconstruction of complex scenes. Robust joint segmentation and reconstruction of dynamic objects is achieved by introducing a geodesic star convexity constraint. Comparative evaluation is performed on a variety of unstructured indoor and outdoor dynamic scenes with hand-held cameras and multiple people. This demonstrates reconstruction of complete temporally coherent 4D scene models with improved nonrigid object segmentation and shape reconstruction.

This record has no associated files available for download.

More information

Accepted/In Press date: 1 April 2016
e-pub ahead of print date: 12 December 2016
Published date: 12 December 2016
Venue - Dates: 2016 IEEE Conference on Computer Vision and Pattern Recognition <br/>, , Las Vegas, United States, 2016-06-27 - 2016-06-30

Identifiers

Local EPrints ID: 438829
URI: http://eprints.soton.ac.uk/id/eprint/438829
ISSN: 1063-6919
PURE UUID: c0395184-65be-4c05-aaa5-43441b734b5f
ORCID for Hansung Kim: ORCID iD orcid.org/0000-0003-4907-0491

Catalogue record

Date deposited: 25 Mar 2020 17:31
Last modified: 17 Mar 2024 04:01

Export record

Altmetrics

Contributors

Author: Armin Mustafa
Author: Hansung Kim ORCID iD
Author: Jean-Yves Guillemaut
Author: Adrian Hilton

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×