Dynamic 3-D facial compression using low rank and sparse decomposition

In this paper, we propose a new compression framework for dynamic 3-D facial expressions acquired from structured light based 3-D camera, based on our previous work. Taking advantage of the near-isometric property of human facial expressions, we parameterize the dynamic 3-D faces into an expression-...

Full description

Saved in:
Bibliographic Details
Main Authors: Chau, Lap-Pui, Hou, Junhui, He, Ying, Quynh, Dao Thi Phuong, Magnenat-Thalmann, Nadia
Other Authors: School of Computer Engineering
Format: Conference or Workshop Item
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/97582
http://hdl.handle.net/10220/12085
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-97582
record_format dspace
spelling sg-ntu-dr.10356-975822020-05-28T07:17:33Z Dynamic 3-D facial compression using low rank and sparse decomposition Chau, Lap-Pui Hou, Junhui He, Ying Quynh, Dao Thi Phuong Magnenat-Thalmann, Nadia School of Computer Engineering School of Electrical and Electronic Engineering Special Interest Group for Computer Graphics Asia Technical Briefs (2012) DRNTU::Engineering::Computer science and engineering In this paper, we propose a new compression framework for dynamic 3-D facial expressions acquired from structured light based 3-D camera, based on our previous work. Taking advantage of the near-isometric property of human facial expressions, we parameterize the dynamic 3-D faces into an expression-invariant canonical domain, which naturally generates geometry video and allows us to apply the well-studied video compression technique. Then, low rank and sparse decomposition is applied to each dimension (i.e., X, Y and Z, respectively) before the H.264/AVC encoder is employed to separately encode each dimension instead of encoding them as a whole. Experimental results show that the averaged 3-4 dB gain is achieved by the proposed scheme compared with existing algorithms. 2013-07-23T09:20:24Z 2019-12-06T19:44:18Z 2013-07-23T09:20:24Z 2019-12-06T19:44:18Z 2012 2012 Conference Paper Hou, J., Chau, L.-P., He, Y., Quynh, D. T. P., & Magnenat-Thalmann, N. (2012). Dynamic 3-D facial compression using low rank and sparse decomposition. SIGGRAPH Asia 2012 Technical Briefs - SA '12. https://hdl.handle.net/10356/97582 http://hdl.handle.net/10220/12085 10.1145/2407746.2407768 en © 2012 ACM.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Chau, Lap-Pui
Hou, Junhui
He, Ying
Quynh, Dao Thi Phuong
Magnenat-Thalmann, Nadia
Dynamic 3-D facial compression using low rank and sparse decomposition
description In this paper, we propose a new compression framework for dynamic 3-D facial expressions acquired from structured light based 3-D camera, based on our previous work. Taking advantage of the near-isometric property of human facial expressions, we parameterize the dynamic 3-D faces into an expression-invariant canonical domain, which naturally generates geometry video and allows us to apply the well-studied video compression technique. Then, low rank and sparse decomposition is applied to each dimension (i.e., X, Y and Z, respectively) before the H.264/AVC encoder is employed to separately encode each dimension instead of encoding them as a whole. Experimental results show that the averaged 3-4 dB gain is achieved by the proposed scheme compared with existing algorithms.
author2 School of Computer Engineering
author_facet School of Computer Engineering
Chau, Lap-Pui
Hou, Junhui
He, Ying
Quynh, Dao Thi Phuong
Magnenat-Thalmann, Nadia
format Conference or Workshop Item
author Chau, Lap-Pui
Hou, Junhui
He, Ying
Quynh, Dao Thi Phuong
Magnenat-Thalmann, Nadia
author_sort Chau, Lap-Pui
title Dynamic 3-D facial compression using low rank and sparse decomposition
title_short Dynamic 3-D facial compression using low rank and sparse decomposition
title_full Dynamic 3-D facial compression using low rank and sparse decomposition
title_fullStr Dynamic 3-D facial compression using low rank and sparse decomposition
title_full_unstemmed Dynamic 3-D facial compression using low rank and sparse decomposition
title_sort dynamic 3-d facial compression using low rank and sparse decomposition
publishDate 2013
url https://hdl.handle.net/10356/97582
http://hdl.handle.net/10220/12085
_version_ 1681056554980212736