Generalized diffusion curves: An improved vector representation for smooth-shaded images Journal Article

Author(s): Jeschke, Stefan
Article Title: Generalized diffusion curves: An improved vector representation for smooth-shaded images
Affiliation IST Austria
Abstract: This paper generalizes the well-known Diffusion Curves Images (DCI), which are composed of a set of Bezier curves with colors specified on either side. These colors are diffused as Laplace functions over the image domain, which results in smooth color gradients interrupted by the Bezier curves. Our new formulation allows for more color control away from the boundary, providing a similar expressive power as recent Bilaplace image models without introducing associated issues and computational costs. The new model is based on a special Laplace function blending and a new edge blur formulation. We demonstrate that given some user-defined boundary curves over an input raster image, fitting colors and edge blur from the image to the new model and subsequent editing and animation is equally convenient as with DCIs. Numerous examples and comparisons to DCIs are presented.
Keywords: Expressive power; Interpolation; color; Curve fitting; Laplace transforms; Boundary curves; Color control; Color gradients; Computational costs; Generalized diffusion; Laplace functions; Vector representations
Journal Title: Computer Graphics Forum
Volume: 35
Issue 2
ISSN: 1467-8659
Publisher: Wiley  
Date Published: 2016-05-01
Start Page: 71
End Page: 79
DOI: 10.1111/cgf.12812
Notes: We thank the anonymous reviewers for their helpful comments and David Hahn for proofreading the paper. We also thank the au- thors of [ OBW ∗ 08 ] and [FSH11] for making their software pub- licly available, which helped us to generate the results and compar- isons. This work was financed by the Austrian Science Fund (FWF) project DEEP PICTURES (no. P24352-N23).
Open access: no
IST Austria Authors
  1. Stefan Jeschke
    11 Jeschke
Related IST Austria Work