Automatic construction of robust spherical harmonic subspaces

Snape, Patrick, Panagakis, Yannis ORCID logoORCID: https://orcid.org/0000-0003-0153-5210 and Zafeiriou, Stefanos (2015) Automatic construction of robust spherical harmonic subspaces. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 07-12 June 2015, Boston, MA, USA. ISBN 9781467369640. ISSN 1063-6919 [Conference or Workshop Item] (doi:10.1109/CVPR.2015.7298604)

[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (1MB) | Preview

Abstract

In this paper we propose a method to automatically recover a class specific low dimensional spherical harmonic basis from a set of in-the-wild facial images. We combine existing techniques for uncalibrated photometric stereo and low rank matrix decompositions in order to robustly recover a combined model of shape and identity. We build this basis without aid from a 3D model and show how it can be combined with recent efficient sparse facial feature localisation techniques to recover dense 3D facial shape. Unlike previous works in the area, our method is very efficient and is an order of magnitude faster to train, taking only a few minutes to build a model with over 2000 images. Furthermore, it can be used for real-time recovery of facial shape.

Item Type: Conference or Workshop Item (Paper)
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 23775
Notes on copyright: © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Useful Links:
Depositing User: Yannis Panagakis
Date Deposited: 06 Mar 2018 19:07
Last Modified: 20 Jun 2022 01:09
URI: https://eprints.mdx.ac.uk/id/eprint/23775

Actions (login required)

View Item View Item

Statistics

Activity Overview
6 month trend
0Downloads
6 month trend
0Hits

Additional statistics are available via IRStats2.