University of Surrey

Test tubes in the lab Research in the ATI Dance Research

U4D: Unsupervised 4D Dynamic Scene Understanding

Mustafa, Armin, Russell, Christopher and Hilton, Adrian (2019) U4D: Unsupervised 4D Dynamic Scene Understanding In: ICCV 2019, 2019-10-27-2019-11-02, Seoul, Korea.

[img] Text
Mustafa_ICCV2019_final.pdf - Accepted version Manuscript
Restricted to Repository staff only until 28 October 2019.

Download (6MB)

Abstract

We introduce the first approach to solve the challenging problem of unsupervised 4D visual scene understanding for complex dynamic scenes with multiple interacting people from multi-view video. Our approach simultaneously estimates a detailed model that includes a per-pixel semantically and temporally coherent reconstruction, together with instance-level segmentation exploiting photo-consistency, semantic and motion information. We further leverage recent advances in 3D pose estimation to constrain the joint semantic instance segmentation and 4D temporally coherent reconstruction. This enables per person semantic instance segmentation of multiple interacting people in complex dynamic scenes. Extensive evaluation of the joint visual scene understanding framework against state-of-the-art methods on challenging indoor and outdoor sequences demonstrates a significant (≈ 40%) improvement in semantic segmentation, reconstruction and scene flow accuracy.

Item Type: Conference or Workshop Item (Conference Poster)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
NameEmailORCID
Mustafa, Armina.mustafa@surrey.ac.uk
Russell, Christopherchris.russell@surrey.ac.uk
Hilton, AdrianA.Hilton@surrey.ac.uk
Date : 22 July 2019
Related URLs :
Depositing User : Diane Maxfield
Date Deposited : 03 Sep 2019 10:23
Last Modified : 03 Sep 2019 10:35
URI: http://epubs.surrey.ac.uk/id/eprint/852525

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