Colorization by example

By Revital Ironi, Daniel Cohen-Or, Dani Lischinski. Eurographics Symposium on Rendering, 2005

378 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/40bb05c3f65fbce3d0b3f56a401892ddca164cd0

How researchers see this paper

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

Citations in the corpus

Color harmonization (2006, methodology): “One of the challenges in these techniques is to recolor the image in a coherent way [Ironi et al. 2005].”
Deep exemplar-based colorization (2018, methodology): “To compare with existing exemplar-based methods [Welsh et al. 2002; Irony et al. 2005; Bugeau et al. 2014; Gupta et al. 2012], we run our algorithm on 35 pairs collected from their papers.”
Deep Colorization (2015, methodology): “6: Comparison with the state-of-art colorization methods [7], [9], [10], [12].”
Let there be color! (2016, methodology): “This technique was improved by us-ing a supervised classiﬁcation scheme that analyzed low-level features [Irony et al. 2005].”
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.”
Real-time user-guided image colorization with learned deep priors (2017, methodology): “Early semi-automatic methods (Chia et al. 2011; Gupta et al. 2012; Irony et al. 2005; Liu et al. 2008; Welsh et al. 2002) utilize an example-based approach that transfers color statistics from a reference image or multiple images (Liu et al. 2014; Mori-moto et al. 2009) to the input grayscale image…”
Colorization Transformer (2021, methodology): “Colorization methods have initially relied on human-in-the-loop approaches to provide hints in the form of scribbles (Levin et al., 2004; Ironi et al., 2005; Huang et al., 2005; Yatziv & Sapiro, 2006; Qu et al., 2006; Luan et al., 2007; Tsaftaris et al., 2014; Zhang et al., 2017; Ci et al., 2018)…”
Self-similarity-based image colorization (2014, background): “The works [5] [6] [7] take as input an example color image with similar textures and color " mood " to the target grayscale image.”
AppProp: all-pairs appearance-space edit propagation (2008, methodology): “Methods based on color labeling have been proposed to address each of these limitations, respectively [Irony et al. 2005] and [Qu et al.”
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, ”
Automatic Image Colorization Via Multimodal Predictions (2008, background): “Note however, if you zoom in, that the contour of the zebra matches exactly boundaries of 2D color regions (purple and pink), whereas in Irony et al.'s result, a several pixel wide band of grass around the zebra's legs and abdomen are colored as if they were part of the zebra.”
Intrinsic colorization (2008, methodology): “In [Irony et al. 2005], a method is presented for automatically generating such scribbles from an example image provided by the user.”
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].”
Data-driven hallucination of different times of day from a single outdoor photo (2013, result): “Example-based Image Colorization Example-based colorization [Irony et al. 2005] automatically generates scribbles from the example image onto the input gray image, and then propagates colors in a way that is similar to [Levin et al.”