Constrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawings

Handle URI:
http://hdl.handle.net/10754/627248
Title:
Constrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawings
Authors:
Shaheen, Sara; Affara, Lama Ahmed; Ghanem, Bernard ( 0000-0002-5534-587X )
Abstract:
Convolutional sparse coding (CSC) plays an essential role in many computer vision applications ranging from image compression to deep learning. In this work, we spot the light on a new application where CSC can effectively serve, namely line drawing analysis. The process of drawing a line drawing can be approximated as the sparse spatial localization of a number of typical basic strokes, which in turn can be cast as a non-standard CSC model that considers the line drawing formation process from parametric curves. These curves are learned to optimize the fit between the model and a specific set of line drawings. Parametric representation of sketches is vital in enabling automatic sketch analysis, synthesis and manipulation. A couple of sketch manipulation examples are demonstrated in this work. Consequently, our novel method is expected to provide a reliable and automatic method for parametric sketch description. Through experiments, we empirically validate the convergence of our method to a feasible solution.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer Science Program; Electrical Engineering Program; Visual Computing Center (VCC)
Citation:
Shaheen S, Affara L, Ghanem B (2017) Constrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawings. 2017 IEEE International Conference on Computer Vision (ICCV). Available: http://dx.doi.org/10.1109/ICCV.2017.474.
Publisher:
IEEE
Journal:
2017 IEEE International Conference on Computer Vision (ICCV)
Conference/Event name:
16th IEEE International Conference on Computer Vision, ICCV 2017
Issue Date:
25-Dec-2017
DOI:
10.1109/ICCV.2017.474
Type:
Conference Paper
Sponsors:
This work was supported by competitive research funding from King Abdullah University of Science and Technology (KAUST).
Additional Links:
http://ieeexplore.ieee.org/document/8237736/
Appears in Collections:
Conference Papers; Computer Science Program; Electrical Engineering Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorShaheen, Saraen
dc.contributor.authorAffara, Lama Ahmeden
dc.contributor.authorGhanem, Bernarden
dc.date.accessioned2018-03-11T06:54:11Z-
dc.date.available2018-03-11T06:54:11Z-
dc.date.issued2017-12-25en
dc.identifier.citationShaheen S, Affara L, Ghanem B (2017) Constrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawings. 2017 IEEE International Conference on Computer Vision (ICCV). Available: http://dx.doi.org/10.1109/ICCV.2017.474.en
dc.identifier.doi10.1109/ICCV.2017.474en
dc.identifier.urihttp://hdl.handle.net/10754/627248-
dc.description.abstractConvolutional sparse coding (CSC) plays an essential role in many computer vision applications ranging from image compression to deep learning. In this work, we spot the light on a new application where CSC can effectively serve, namely line drawing analysis. The process of drawing a line drawing can be approximated as the sparse spatial localization of a number of typical basic strokes, which in turn can be cast as a non-standard CSC model that considers the line drawing formation process from parametric curves. These curves are learned to optimize the fit between the model and a specific set of line drawings. Parametric representation of sketches is vital in enabling automatic sketch analysis, synthesis and manipulation. A couple of sketch manipulation examples are demonstrated in this work. Consequently, our novel method is expected to provide a reliable and automatic method for parametric sketch description. Through experiments, we empirically validate the convergence of our method to a feasible solution.en
dc.description.sponsorshipThis work was supported by competitive research funding from King Abdullah University of Science and Technology (KAUST).en
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/document/8237736/en
dc.titleConstrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawingsen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentComputer Science Programen
dc.contributor.departmentElectrical Engineering Programen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journal2017 IEEE International Conference on Computer Vision (ICCV)en
dc.conference.date2017-10-22 to 2017-10-29en
dc.conference.name16th IEEE International Conference on Computer Vision, ICCV 2017en
dc.conference.locationVenice, ITAen
kaust.authorShaheen, Saraen
kaust.authorAffara, Lama Ahmeden
kaust.authorGhanem, Bernarden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.