Probabilistic Image Colorization
This addresses the uncertainty in image colorization for computer vision applications, offering a novel stochastic approach.
The paper tackles the problem of colorizing grayscale natural images by developing a probabilistic framework that produces multiple plausible and vivid colorizations, demonstrating strong results on CIFAR-10 and ILSVRC 2012 datasets.
We develop a probabilistic technique for colorizing grayscale natural images. In light of the intrinsic uncertainty of this task, the proposed probabilistic framework has numerous desirable properties. In particular, our model is able to produce multiple plausible and vivid colorizations for a given grayscale image and is one of the first colorization models to provide a proper stochastic sampling scheme. Moreover, our training procedure is supported by a rigorous theoretical framework that does not require any ad hoc heuristics and allows for efficient modeling and learning of the joint pixel color distribution. We demonstrate strong quantitative and qualitative experimental results on the CIFAR-10 dataset and the challenging ILSVRC 2012 dataset.