• 1 Citations

Abstract

Non-rigid video interpolation is a common computer vision task. In this paper we present an optical flow approach which adopts a Laplacian Cotangent Mesh constraint to enhance the local smoothness. Similar to Li et al., our approach adopts a mesh to the image with a resolution up to one vertex per pixel and uses angle constraints to ensure sensible local deformations between image pairs. The Laplacian Mesh constraints are expressed wholly inside the optical flow optimization, and can be applied in a straightforward manner to a wide range of image tracking and registration problems. We evaluate our approach by testing on several benchmark datasets, including the Middlebury and Garg et al. datasets. In addition, we show application of our method for constructing 3D Morphable Facial Models from dynamic 3D data.
LanguageEnglish
Pages236-243
JournalNeurocomputing
Volume220
Early online date29 Sep 2016
DOIs
StatusPublished - 12 Jan 2017

Fingerprint

Optical flows
Interpolation
Benchmarking
Computer vision
Pixels
Testing
Datasets

Cite this

Video interpolation using optical flow and Laplacian smoothness. / Li, Wenbin; Cosker, Darren.

In: Neurocomputing, Vol. 220, 12.01.2017, p. 236-243.

Research output: Contribution to journalArticle

@article{34f9baf50bfd43b5820af4d859826413,
title = "Video interpolation using optical flow and Laplacian smoothness",
abstract = "Non-rigid video interpolation is a common computer vision task. In this paper we present an optical flow approach which adopts a Laplacian Cotangent Mesh constraint to enhance the local smoothness. Similar to Li et al., our approach adopts a mesh to the image with a resolution up to one vertex per pixel and uses angle constraints to ensure sensible local deformations between image pairs. The Laplacian Mesh constraints are expressed wholly inside the optical flow optimization, and can be applied in a straightforward manner to a wide range of image tracking and registration problems. We evaluate our approach by testing on several benchmark datasets, including the Middlebury and Garg et al. datasets. In addition, we show application of our method for constructing 3D Morphable Facial Models from dynamic 3D data.",
author = "Wenbin Li and Darren Cosker",
year = "2017",
month = "1",
day = "12",
doi = "10.1016/j.neucom.2016.04.064",
language = "English",
volume = "220",
pages = "236--243",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

TY - JOUR

T1 - Video interpolation using optical flow and Laplacian smoothness

AU - Li, Wenbin

AU - Cosker, Darren

PY - 2017/1/12

Y1 - 2017/1/12

N2 - Non-rigid video interpolation is a common computer vision task. In this paper we present an optical flow approach which adopts a Laplacian Cotangent Mesh constraint to enhance the local smoothness. Similar to Li et al., our approach adopts a mesh to the image with a resolution up to one vertex per pixel and uses angle constraints to ensure sensible local deformations between image pairs. The Laplacian Mesh constraints are expressed wholly inside the optical flow optimization, and can be applied in a straightforward manner to a wide range of image tracking and registration problems. We evaluate our approach by testing on several benchmark datasets, including the Middlebury and Garg et al. datasets. In addition, we show application of our method for constructing 3D Morphable Facial Models from dynamic 3D data.

AB - Non-rigid video interpolation is a common computer vision task. In this paper we present an optical flow approach which adopts a Laplacian Cotangent Mesh constraint to enhance the local smoothness. Similar to Li et al., our approach adopts a mesh to the image with a resolution up to one vertex per pixel and uses angle constraints to ensure sensible local deformations between image pairs. The Laplacian Mesh constraints are expressed wholly inside the optical flow optimization, and can be applied in a straightforward manner to a wide range of image tracking and registration problems. We evaluate our approach by testing on several benchmark datasets, including the Middlebury and Garg et al. datasets. In addition, we show application of our method for constructing 3D Morphable Facial Models from dynamic 3D data.

UR - http://dx.doi.org/10.1016/j.neucom.2016.04.064

U2 - 10.1016/j.neucom.2016.04.064

DO - 10.1016/j.neucom.2016.04.064

M3 - Article

VL - 220

SP - 236

EP - 243

JO - Neurocomputing

T2 - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -