A Training-Free Mesh Upsampling and Morphing Technique for 3D Face Rejuvenation

Syed Shah, Mohammed Bennamoun, Michael Molton

Research output: Chapter in Book/Conference paperConference paper

Abstract

Mesh upsampling and morphing is a challenging
problem due to the irregularity and sparseness of the 3D
data. Unlike 2D grid of pixels, 3D points do not have any
regular structure and spatial order. In this paper, we present
an efficient mesh upsampling and morphing technique. The
proposed technique does not require training and does not rely
on any particular upsampling model. The key idea is to select and
process each mesh triangle based on a heuristic criteria to define
the 3D coordinate of a new point. An interactive mesh morphing
technique is also introduced to test the effectiveness of the mesh
upsampling algorithm. We perform quantitative and qualitative
analysis to evaluate the performance of our proposed technique.
Our empirical results show that our upsampled points have better
uniformity and are located closer to the underlying surfaces.
The computational time analysis demonstrates that the proposed
technique is very efficient. The average mesh upsampling time
is only 2.11sec which makes the proposed technique suitable for
real time applications. To further demonstrate the effectiveness
of our proposed technique, we evaluate it for a novel task of
facial rejuvenation prediction and report our preliminary results
in this paper.
Original languageEnglish
Title of host publication2018 International Conference on Image and Vision Computing New Zealand (IVCNZ)
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISBN (Electronic)9781728101255
DOIs
Publication statusPublished - 7 Feb 2019
Event2018 International Conference on Image and Vision Computing New Zealand (IVCNZ) - Auckland, New Zealand
Duration: 19 Nov 201821 Nov 2018

Publication series

NameInternational Conference Image and Vision Computing New Zealand
Volume2018-November
ISSN (Print)2151-2191
ISSN (Electronic)2151-2205

Conference

Conference2018 International Conference on Image and Vision Computing New Zealand (IVCNZ)
CountryNew Zealand
CityAuckland
Period19/11/1821/11/18

Fingerprint

Pixels

Cite this

Shah, S., Bennamoun, M., & Molton, M. (2019). A Training-Free Mesh Upsampling and Morphing Technique for 3D Face Rejuvenation. In 2018 International Conference on Image and Vision Computing New Zealand (IVCNZ) [8634685] (International Conference Image and Vision Computing New Zealand; Vol. 2018-November). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IVCNZ.2018.8634685
Shah, Syed ; Bennamoun, Mohammed ; Molton, Michael. / A Training-Free Mesh Upsampling and Morphing Technique for 3D Face Rejuvenation. 2018 International Conference on Image and Vision Computing New Zealand (IVCNZ). IEEE, Institute of Electrical and Electronics Engineers, 2019. (International Conference Image and Vision Computing New Zealand).
@inproceedings{f597970b9aa34954a34a97d6095599cc,
title = "A Training-Free Mesh Upsampling and Morphing Technique for 3D Face Rejuvenation",
abstract = "Mesh upsampling and morphing is a challengingproblem due to the irregularity and sparseness of the 3Ddata. Unlike 2D grid of pixels, 3D points do not have anyregular structure and spatial order. In this paper, we presentan efficient mesh upsampling and morphing technique. Theproposed technique does not require training and does not relyon any particular upsampling model. The key idea is to select andprocess each mesh triangle based on a heuristic criteria to definethe 3D coordinate of a new point. An interactive mesh morphingtechnique is also introduced to test the effectiveness of the meshupsampling algorithm. We perform quantitative and qualitativeanalysis to evaluate the performance of our proposed technique.Our empirical results show that our upsampled points have betteruniformity and are located closer to the underlying surfaces.The computational time analysis demonstrates that the proposedtechnique is very efficient. The average mesh upsampling timeis only 2.11sec which makes the proposed technique suitable forreal time applications. To further demonstrate the effectivenessof our proposed technique, we evaluate it for a novel task offacial rejuvenation prediction and report our preliminary resultsin this paper.",
author = "Syed Shah and Mohammed Bennamoun and Michael Molton",
year = "2019",
month = "2",
day = "7",
doi = "10.1109/IVCNZ.2018.8634685",
language = "English",
series = "International Conference Image and Vision Computing New Zealand",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
booktitle = "2018 International Conference on Image and Vision Computing New Zealand (IVCNZ)",
address = "United States",

}

Shah, S, Bennamoun, M & Molton, M 2019, A Training-Free Mesh Upsampling and Morphing Technique for 3D Face Rejuvenation. in 2018 International Conference on Image and Vision Computing New Zealand (IVCNZ)., 8634685, International Conference Image and Vision Computing New Zealand, vol. 2018-November, IEEE, Institute of Electrical and Electronics Engineers, 2018 International Conference on Image and Vision Computing New Zealand (IVCNZ), Auckland, New Zealand, 19/11/18. https://doi.org/10.1109/IVCNZ.2018.8634685

A Training-Free Mesh Upsampling and Morphing Technique for 3D Face Rejuvenation. / Shah, Syed; Bennamoun, Mohammed; Molton, Michael.

2018 International Conference on Image and Vision Computing New Zealand (IVCNZ). IEEE, Institute of Electrical and Electronics Engineers, 2019. 8634685 (International Conference Image and Vision Computing New Zealand; Vol. 2018-November).

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - A Training-Free Mesh Upsampling and Morphing Technique for 3D Face Rejuvenation

AU - Shah, Syed

AU - Bennamoun, Mohammed

AU - Molton, Michael

PY - 2019/2/7

Y1 - 2019/2/7

N2 - Mesh upsampling and morphing is a challengingproblem due to the irregularity and sparseness of the 3Ddata. Unlike 2D grid of pixels, 3D points do not have anyregular structure and spatial order. In this paper, we presentan efficient mesh upsampling and morphing technique. Theproposed technique does not require training and does not relyon any particular upsampling model. The key idea is to select andprocess each mesh triangle based on a heuristic criteria to definethe 3D coordinate of a new point. An interactive mesh morphingtechnique is also introduced to test the effectiveness of the meshupsampling algorithm. We perform quantitative and qualitativeanalysis to evaluate the performance of our proposed technique.Our empirical results show that our upsampled points have betteruniformity and are located closer to the underlying surfaces.The computational time analysis demonstrates that the proposedtechnique is very efficient. The average mesh upsampling timeis only 2.11sec which makes the proposed technique suitable forreal time applications. To further demonstrate the effectivenessof our proposed technique, we evaluate it for a novel task offacial rejuvenation prediction and report our preliminary resultsin this paper.

AB - Mesh upsampling and morphing is a challengingproblem due to the irregularity and sparseness of the 3Ddata. Unlike 2D grid of pixels, 3D points do not have anyregular structure and spatial order. In this paper, we presentan efficient mesh upsampling and morphing technique. Theproposed technique does not require training and does not relyon any particular upsampling model. The key idea is to select andprocess each mesh triangle based on a heuristic criteria to definethe 3D coordinate of a new point. An interactive mesh morphingtechnique is also introduced to test the effectiveness of the meshupsampling algorithm. We perform quantitative and qualitativeanalysis to evaluate the performance of our proposed technique.Our empirical results show that our upsampled points have betteruniformity and are located closer to the underlying surfaces.The computational time analysis demonstrates that the proposedtechnique is very efficient. The average mesh upsampling timeis only 2.11sec which makes the proposed technique suitable forreal time applications. To further demonstrate the effectivenessof our proposed technique, we evaluate it for a novel task offacial rejuvenation prediction and report our preliminary resultsin this paper.

U2 - 10.1109/IVCNZ.2018.8634685

DO - 10.1109/IVCNZ.2018.8634685

M3 - Conference paper

T3 - International Conference Image and Vision Computing New Zealand

BT - 2018 International Conference on Image and Vision Computing New Zealand (IVCNZ)

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Shah S, Bennamoun M, Molton M. A Training-Free Mesh Upsampling and Morphing Technique for 3D Face Rejuvenation. In 2018 International Conference on Image and Vision Computing New Zealand (IVCNZ). IEEE, Institute of Electrical and Electronics Engineers. 2019. 8634685. (International Conference Image and Vision Computing New Zealand). https://doi.org/10.1109/IVCNZ.2018.8634685