Let there be color!
- 11 July 2016
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 35 (4), 1-11
- https://doi.org/10.1145/2897824.2925974
Abstract
We present a novel technique to automatically colorize grayscale images that combines both global priors and local image features. Based on Convolutional Neural Networks, our deep network features a fusion layer that allows us to elegantly merge local information dependent on small image patches with global priors computed using the entire image. The entire framework, including the global and local priors as well as the colorization model, is trained in an end-to-end fashion. Furthermore, our architecture can process images of any resolution, unlike most existing approaches based on CNN. We leverage an existing large-scale scene classification database to train our model, exploiting the class labels of the dataset to more efficiently and discriminatively learn the global priors. We validate our approach with a user study and compare against the state of the art, where we show significant improvements. Furthermore, we demonstrate our method extensively on many different types of images, including black-and-white photography from over a hundred years ago, and show realistic colorizations.Keywords
This publication has 31 references indexed in Scilit:
- Instant Propagation of Sparse Edits on Images and VideosComputer Graphics Forum, 2010
- Efficient affinity-based edit propagation using K-D treeACM Transactions on Graphics, 2009
- LazyBrush: Flexible Painting Tool for Hand‐drawn CartoonsComputer Graphics Forum, 2009
- Intrinsic colorizationACM Transactions on Graphics, 2008
- Animating animal motion from stillACM Transactions on Graphics, 2008
- AppPropACM Transactions on Graphics, 2008
- Automated colour grading using colour distribution transferComputer Vision and Image Understanding, 2007
- Manga colorizationACM Transactions on Graphics, 2006
- Transferring color to greyscale imagesACM Transactions on Graphics, 2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998