Transferring color to greyscale images

By Tom Welsh, Michael Ashikhmin, Klaus Mueller. 2002

941 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Colorful Image Colorization (2016, methodology): “First, color reference images are provided by the user [3,6,7] or automatically retrieved with user-supplied metadata [8,9].”
Learning Representations for Automatic Colorization (2016, methodology): “This can be seen as an extension of patch-matching techniques [41], adding interaction terms for spatial consistency.”
Tracking Emerges by Colorizing Videos (2018, background): “Colorization: The task of colorizing gray-scale images has been the subject of signiﬁcant study in the computer vision community [25–34], which inspired this paper.”
Colorization by example (2005, methodology): “The method of Welsh et al. [WAM02], which was discussed in the previous section, could be viewed as an extension of Rein-hard’s approach to the task of colorization.”
PixColor: Pixel Recursive Colorization (2017, background): “Early approaches to colorization relied on some amount of human effort, either to identify a relevant source color image from which the colors could be transferred [3, 6, 13, 16, 24, 25, 28, 33, 39], or to get a rough coloring from a human annotator to serve as a set of "hints" [11, 14, 21, 22, 26, ”
Automated colour grading using colour distribution transfer (2007, methodology): “One automated solution is to invoke the spatial information of the images to constrain the colour mapping [18] [19] [20].”
Fast image and video colorization using chrominance blending (2006, methodology): “technique also uses as input observed values of the chrominance channels in a region c2 which is significantly smaller than (see [ 12 ]).”
Learning Large-Scale Automatic Image Colorization (2015, methodology): “demonstrated that their image analogies method could be used to colorize [7], and the approach was extended by Welsh [19] by introducing different normalization and matching step.”
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].”
Colorization Transformer (2021, background): “…et al., 2017; Ci et al., 2018) and exemplar-based techniques that involve identifying a reference source image to copy colors from (Reinhard et al., 2001; Welsh et al., 2002; Tai et al., 2005; Ironi et al., 2005; Pitié et al., 2007; Morimoto et al., 2009; Gupta et al., 2012; Xiao et al., 2020).”
N-dimensional probability density function transfer and its application to color transfer (2005, background): “Retrieving the missing chrominance channels values can be done by taking advantage of similarities between spatial neighbourhoods of the two pictures [16] [6].”
Image colorization using similar images (2012, methodology): “Speciﬁcally, other than intensity and standard deviation features which are used by other colorization methods e.g. [17, 8], we incorporate the highly discriminative et al. where they exploit SIFT features to ﬁnd correspondences between images for scene alignment.”
Deep Colorization (2015, methodology): “6: Comparison with the state-of-art colorization methods [7], [9], [10], [12].”