Empirical Inference

Automatic Image Colorization Via Multimodal Predictions

2008

Conference Paper

ei


We aim to color automatically greyscale images, without any manual intervention. The color proposition could then be interactively corrected by user-provided color landmarks if necessary. Automatic colorization is nontrivial since there is usually no one-to-one correspondence between color and local texture. The contribution of our framework is that we deal directly with multimodality and estimate, for each pixel of the image to be colored, the probability distribution of all possible colors, instead of choosing the most probable color at the local level. We also predict the expected variation of color at each pixel, thus defining a nonuniform spatial coherency criterion. We then use graph cuts to maximize the probability of the whole colored image at the global level. We work in the L-a-b color space in order to approximate the human perception of distances between colors, and we use machine learning tools to extract as much information as possible from a dataset of colored examples. The resulting algorithm is fast, designed to be more robust to texture noise, and is above all able to deal with ambiguity, in contrary to previous approaches.

Author(s): Charpiat, G. and Hofmann, M. and Schölkopf, B.
Book Title: Computer Vision - ECCV 2008, Lecture Notes in Computer Science, Vol. 5304
Journal: Computer Vision: ECCV 2008
Pages: 126-139
Year: 2008
Month: October
Day: 0
Editors: DA Forsyth and PHS Torr and A Zisserman
Publisher: Springer

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1007/978-3-540-88690-7_10
Event Name: 10th European Conference on Computer Vision
Event Place: Marseille, France

Address: Berlin, Germany
Digital: 0
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@inproceedings{5300,
  title = {Automatic Image Colorization Via Multimodal Predictions},
  author = {Charpiat, G. and Hofmann, M. and Sch{\"o}lkopf, B.},
  journal = {Computer Vision: ECCV 2008},
  booktitle = {Computer Vision - ECCV 2008, Lecture Notes in Computer Science, Vol. 5304},
  pages = {126-139},
  editors = {DA Forsyth and PHS Torr and A Zisserman},
  publisher = {Springer},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Berlin, Germany},
  month = oct,
  year = {2008},
  doi = {10.1007/978-3-540-88690-7_10},
  month_numeric = {10}
}