HAL - INRIA :: [inria-00274768, version 1] Diffusion Curves: A Vector Representation for Smooth-Shaded Images

inria-00274768, version 1

Diffusion Curves: A Vector Representation for Smooth-Shaded Images

Alexandrina Orzan () ¹, Adrien Bousseau ()^a^, 1, Holger Winnemöller^b^, 2, Pascal Barla () ^3, 4, Joëlle Thollot ()^c^, 1, 5, David Salesin^b^, 2

ACM Transactions on Graphics (Proceedings of SIGGRAPH 2008) 27, 3 (2008) 92-92:8

Abstract: We describe a new vector-based primitive for creating smooth-shaded images, called the diffusion curve. A diffusion curve partitions the space through which it is drawn, defining different colors on either side. These colors may vary smoothly along the curve. In addition, the sharpness of the color transition from one side of the curve to the other can be controlled. Given a set of diffusion curves, the final image is constructed by solving a Poisson equation whose constraints are specified by the set of gradients across all diffusion curves. Like all vector-based primitives, diffusion curves conveniently support a variety of operations, including geometry-based editing, keyframe animation, and ready stylization. Moreover, their representation is compact and inherently resolution-independent. We describe a GPU-based implementation for rendering images defined by a set of diffusion curves in realtime. We then demonstrate an interactive drawing system for allowing artists to create artworks using diffusion curves, either by drawing the curves in a freehand style, or by tracing existing imagery. The system is simple and intuitive: we show results created by artists after just a few minutes of instruction. Furthermore, we describe a completely automatic conversion process for taking an image and turning it into a set of diffusion curves that closely approximate the original image content.

a – MENRT
b – Adobe Systems
c – Institut National Polytechnique de Grenoble - INPG
1: ARTIS (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
CNRS : FR71 – INRIA – Laboratoire Jean Kuntzmann – CNRS : UMR5224 – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)
2: Adobe Systems Inc. (Adobe Advanced Technology Labs)
Adobe Systems Inc.
3: IPARLA (INRIA Bordeaux - Sud-Ouest)
INRIA – CNRS : UMR5800 – École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB) – Université Sciences et Technologies - Bordeaux I
4: Laboratoire Bordelais de Recherche en Informatique (LaBRI)
CNRS : UMR5800 – Université Sciences et Technologies - Bordeaux I – École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB) – Université Victor Segalen - Bordeaux II
5: Laboratoire Jean Kuntzmann (LJK)
CNRS : UMR5224 – Université Joseph Fourier - Grenoble I – Université Pierre Mendès-France - Grenoble II – Institut Polytechnique de Grenoble - Grenoble Institute of Technology

inria-00274768, version 1
http://hal.inria.fr/inria-00274768
oai:hal.inria.fr:inria-00274768
From: Pascal Barla <>
Submitted on: Tuesday, 14 June 2011 11:02:09
Updated on: Tuesday, 10 April 2012 09:08:16

See detailed view

Associated documents

PDF :

VIDEO :

Annexes :

Export

Bibtex EndNote TEI RefWorks

%% inria-00274768, version 1
%% http://hal.inria.fr/inria-00274768
@article{orzan:inria-00274768,
    hal_id = {inria-00274768},
    url = {http://hal.inria.fr/inria-00274768},
    title = {{Diffusion Curves: A Vector Representation for Smooth-Shaded Images}},
    author = {Orzan, Alexandrina and Bousseau, Adrien and Winnem{\"o}ller, Holger and Barla, Pascal and Thollot, Jo{\"e}lle and Salesin, David},
    abstract = {{We describe a new vector-based primitive for creating smooth-shaded images, called the diffusion curve. A diffusion curve partitions the space through which it is drawn, defining different colors on either side. These colors may vary smoothly along the curve. In addition, the sharpness of the color transition from one side of the curve to the other can be controlled. Given a set of diffusion curves, the final image is constructed by solving a Poisson equation whose constraints are specified by the set of gradients across all diffusion curves. Like all vector-based primitives, diffusion curves conveniently support a variety of operations, including geometry-based editing, keyframe animation, and ready stylization. Moreover, their representation is compact and inherently resolution-independent. We describe a GPU-based implementation for rendering images defined by a set of diffusion curves in realtime. We then demonstrate an interactive drawing system for allowing artists to create artworks using diffusion curves, either by drawing the curves in a freehand style, or by tracing existing imagery. The system is simple and intuitive: we show results created by artists after just a few minutes of instruction. Furthermore, we describe a completely automatic conversion process for taking an image and turning it into a set of diffusion curves that closely approximate the original image content.}},
    keywords = {Vector graphics; vectorization; gradient mesh; color diffusion; image creation; image reconstruction},
    language = {English},
    affiliation = {ARTIS - INRIA Grenoble Rh{\^o}ne-Alpes / LJK Laboratoire Jean Kuntzmann , Adobe Systems Inc. - Adobe Advanced Technology Labs , IPARLA - INRIA Bordeaux - Sud-Ouest , Laboratoire Bordelais de Recherche en Informatique - LaBRI , Laboratoire Jean Kuntzmann - LJK},
    booktitle = {{Proceedings of ACM SIGGRAPH 2008}},
    publisher = {ACM},
    pages = {92-92:8},
    journal = {ACM Transactions on Graphics (Proceedings of SIGGRAPH 2008)},
    volume = {27},
    number = {3 },
    audience = {international },
    year = {2008},
    month = Aug,
    pdf = {http://hal.inria.fr/inria-00274768/PDF/diffusion\_curves.pdf},
}

%F inria-00274768, version 1
%0 Journal Article
%U http://hal.inria.fr/inria-00274768
%2 INFO:INFO_GR
%T Diffusion Curves: A Vector Representation for Smooth-Shaded Images
%A Orzan, Alexandrina
%A Bousseau, Adrien
%A Winnemöller, Holger
%A Barla, Pascal
%A Thollot, Joëlle
%A Salesin, David
%+ ARTIS - INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann , Adobe Systems Inc. - Adobe Advanced Technology Labs , IPARLA - INRIA Bordeaux - Sud-Ouest , Laboratoire Bordelais de Recherche en Informatique - LaBRI , Laboratoire Jean Kuntzmann - LJK
%X We describe a new vector-based primitive for creating smooth-shaded images, called the diffusion curve. A diffusion curve partitions the space through which it is drawn, defining different colors on either side. These colors may vary smoothly along the curve. In addition, the sharpness of the color transition from one side of the curve to the other can be controlled. Given a set of diffusion curves, the final image is constructed by solving a Poisson equation whose constraints are specified by the set of gradients across all diffusion curves. Like all vector-based primitives, diffusion curves conveniently support a variety of operations, including geometry-based editing, keyframe animation, and ready stylization. Moreover, their representation is compact and inherently resolution-independent. We describe a GPU-based implementation for rendering images defined by a set of diffusion curves in realtime. We then demonstrate an interactive drawing system for allowing artists to create artworks using diffusion curves, either by drawing the curves in a freehand style, or by tracing existing imagery. The system is simple and intuitive: we show results created by artists after just a few minutes of instruction. Furthermore, we describe a completely automatic conversion process for taking an image and turning it into a set of diffusion curves that closely approximate the original image content.
%G English
%J ACM Transactions on Graphics (Proceedings of SIGGRAPH 2008)
%8 2008-08-00
%2 international
%I ACM
%2 Proceedings of ACM SIGGRAPH 2008
%V 27
%N 3
%P 92-92:8
%2 http://artis.imag.fr/Publications/2008/OBWBTS08/info.html
%K Vector graphics; vectorization; gradient mesh; color diffusion; image creation; image reconstruction

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="article"><head>Articles in peer-reviewed journal</head>
<biblStruct type="article" xml:id="inria-00274768"><analytic>
<author><persName><forename>Alexandrina</forename><surname>Orzan</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann</orgName>
<orgName type="team">ARTIS</orgName>
<country>FR</country>
<orgName type="institution">CNRS : FR71</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Laboratoire Jean Kuntzmann</orgName>
<orgName type="institution">CNRS : UMR5224</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Institut National Polytechnique de Grenoble (INPG)</orgName>
</affiliation>
</author>
<author><persName><forename>Adrien</forename><surname>Bousseau</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann</orgName>
<orgName type="team">ARTIS</orgName>
<country>FR</country>
<orgName type="institution">CNRS : FR71</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Laboratoire Jean Kuntzmann</orgName>
<orgName type="institution">CNRS : UMR5224</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Institut National Polytechnique de Grenoble (INPG)</orgName>
</affiliation>
</author>
<author><persName><forename>Holger</forename><surname>Winnemöller</surname></persName>
<affiliation>
<orgName type="laboratory">Adobe Advanced Technology Labs</orgName>
<orgName type="team">Adobe Systems Inc.</orgName>
<country>US</country>
<orgName type="institution">Adobe Systems Inc.</orgName>
</affiliation>
</author>
<author><persName><forename>Pascal</forename><surname>Barla</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Bordeaux - Sud-Ouest</orgName>
<orgName type="team">IPARLA</orgName>
<country>FR</country>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">CNRS : UMR5800</orgName>
<orgName type="institution">École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)</orgName>
<orgName type="institution">Université Sciences et Technologies - Bordeaux I</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">LaBRI</orgName>
<orgName type="team">Laboratoire Bordelais de Recherche en Informatique</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR5800</orgName>
<orgName type="institution">Université Sciences et Technologies - Bordeaux I</orgName>
<orgName type="institution">École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)</orgName>
<orgName type="institution">Université Victor Segalen - Bordeaux II</orgName>
</affiliation>
</author>
<author><persName><forename>Joëlle</forename><surname>Thollot</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann</orgName>
<orgName type="team">ARTIS</orgName>
<country>FR</country>
<orgName type="institution">CNRS : FR71</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Laboratoire Jean Kuntzmann</orgName>
<orgName type="institution">CNRS : UMR5224</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Institut National Polytechnique de Grenoble (INPG)</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">LJK</orgName>
<orgName type="team">Laboratoire Jean Kuntzmann</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR5224</orgName>
<orgName type="institution">Université Joseph Fourier - Grenoble I</orgName>
<orgName type="institution">Université Pierre Mendès-France - Grenoble II</orgName>
<orgName type="institution">Institut Polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
</affiliation>
</author>
<author><persName><forename>David</forename><surname>Salesin</surname></persName>
<affiliation>
<orgName type="laboratory">Adobe Advanced Technology Labs</orgName>
<orgName type="team">Adobe Systems Inc.</orgName>
<country>US</country>
<orgName type="institution">Adobe Systems Inc.</orgName>
</affiliation>
</author>
<title type="main" level="a">Diffusion Curves: A Vector Representation for Smooth-Shaded Images</title></analytic><monogr><title level="j" type="main">ACM Transactions on Graphics (Proceedings of SIGGRAPH 2008)</title><imprint><publisher>ACM</publisher><biblScope type="publicationDate">2008-08-00</biblScope><biblScope type="vol">27</biblScope><biblScope type="issue">3</biblScope><biblScope type="pp">92-92:8</biblScope></imprint></monogr><idno type="HALid">http://hal.inria.fr/inria-00274768</idno><idno type="HALFile">http://hal.inria.fr/inria-00274768/PDF/diffusion_curves.pdf</idno></biblStruct>
</listBibl>
</listBibl>

Diffusion Curves: A Vector Representation for Smooth-Shaded Images

Associated documents

See also

Export