Visual
Computing

Generalized Diffusion Curves: An Improved Vector Representation for Smooth-Shaded Images

GDCI example
Given an input image (top-left) and Bezier curves (top-right), our algorithm automatically fits color values to the curves control points so that the result look close to the input image (bottom-right). This representation can be edited (bottom-left). Please also see our video.

Authors

Affiliations

Publication

Computer Graphics Forum (Eurographics 2016)

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.

Citation

@article{GDCI2016,
author = {Stefan Jeschke},
title = {Generalized Diffusion Curves: An Improved Vector Representation for Smooth-Shaded Images},
journal = {Computer Graphics Forum},
year = {2016},
volume = {35},
number = {2},
pages = {1--9}
}

Acknowledgements

Thanks go to David Hahn for help proofreading the paper, and to the IST Austria Visual Computing group for helpful feedback throughout the project.

This project has received funding from Austrian Science Fund (FWF) standalone project ‘Deep Pictures’ No. P24352-N23.