Automatic Image Colorization Via Multimodal Predictions

By Guillaume Charpiat, Matthias Hofmann, Bernhard Schölkopf. 2008

265 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Social Psychology, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Social Psychology

In Multimodal Learning

Citations in the corpus

Colorful Image Colorization (2016, methodology): “As pointed out by [3], color prediction is inherently multimodal – many objects, such as a shirt, can plausibly be colored one of several distinct values.”
Learning Representations for Automatic Colorization (2016, methodology): “Mapping between source and target is established automatically, using correspondences between local descriptors [3, 26, 41], or in combination with manual intervention [6, 19].”
Real-time user-guided image colorization with learned deep priors (2017, background): “However, these approaches aim to produce a single plausible result, even though colorization is intrinsically an ill-posed problem with multi-modal uncertainty (Charpiat et al. 2008).”
Diverse Image Synthesis From Semantic Layouts via Conditional IMLE (2018, methodology): “A number of methods for colourization [2, 38, 19] predict a discretized marginal distribution over colours of each individual pixel.”
PixColor: Pixel Recursive Colorization (2017, methodology): “One approach is to use a conditional random ﬁeld (CRF) [3], although inference in such models can be slow.”
Learning Large-Scale Automatic Image Colorization (2015, background): “predict multiple colors for each pixel by estimating conditional probabilities over texture features and enforce smoothness using graph-cuts to find globally optimal colors [4].”
Deep Colorization (2015, methodology): “6: Comparison with the state-of-art colorization methods [7], [9], [10], [12].”
Semantic colorization with internet images (2011, methodology): “This compares favorably to the 48.90% obtained by [Welsh et al. 2002], 32.30% by [Charpiat et al. 2008] and 40.79% by [Tai et al. 2005].”
Image colorization using similar images (2012, methodology): “Charpiat [2] assign colors to a gray image by an energy function Liu et al. [12] proposed an example-based colorization technique which is robust to illumination target and reference images.”