A Framework for Interactive Image Color Editing

Przemyslaw Musialski, Ming Cui, Jieping Ye, Anshuman Razdan, Peter Wonka
A Framework for Interactive Image Color Editing
The Visual Computer, 29(11):1173-1186, November 2012. [draft]

Information

Abstract

We propose a new method for interactive image color replacement that creates smooth and naturally looking results with minimal user interaction. Our system expects as input a source image and rawly scribbled target color values and generates high quality results in interactive rates. To achieve this goal we introduce an algorithm that preserves pairwise distances of the signatures in the original image and simultaneously maps the color to the user defined target values. We propose efficient sub-sampling in order to reduce the computational load and adapt semi-supervised locally linear embedding to optimize the constraints in one objective function. We show the application of the algorithm on typical photographs and compare the results to other color replacement methods.

Additional Files and Images

Additional images and videos

comparison: comparison to other methods comparison: comparison to other methods
results: results of the proposed method results: results of the proposed method

Additional files

code: MATLAB code code: MATLAB code
draft: paper draft [8MB] draft: paper draft [8MB]

Weblinks

BibTeX

@article{musialski_2012_fice,
  title =      "A Framework for Interactive Image Color Editing",
  author =     "Przemyslaw Musialski and Ming Cui and Jieping Ye and
               Anshuman Razdan and Peter Wonka",
  year =       "2012",
  abstract =   "We propose a new method for interactive image color
               replacement that creates smooth and naturally looking
               results with minimal user interaction. Our system expects as
               input a source image and rawly scribbled target color values
               and generates high quality results in interactive rates. To
               achieve this goal we introduce an algorithm that preserves
               pairwise distances of the signatures in the original image
               and simultaneously maps the color to the user defined target
               values. We propose efficient sub-sampling in order to reduce
               the computational load and adapt semi-supervised locally
               linear embedding to optimize the constraints in one
               objective function. We show the application of the algorithm
               on typical photographs and compare the results to other
               color replacement methods.",
  month =      nov,
  journal =    "The Visual Computer",
  number =     "11",
  volume =     "29",
  pages =      "1173--1186",
  keywords =   "interactive image editing, color manipulation, image
               processing, recoloring, computational photography",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2012/musialski_2012_fice/",
}