Automatic Image Colorization Via Multimodal Predictions

We aim to color greyscale images automatically, 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. ...

• Type: Conference
• Year: 2008
• Where: ECCV
• Authors: Bernhard Schölkopf, Guillaume Charpiat, Matthias Hofmann
• Keywords: Color Proposition, Computer Vision, ECCV 2008, L-a-b Color Space, Nonuniform Spatial Coherency, Probable Color, User-provided Color Landmarks