Learning Representations for Automatic Colorization
Preprint
Abstract
We develop a fully automatic image colorization system. Our approach leverages recent advances in deep networks, exploiting both low-level and semantic representations. As many scene elements naturally appear according to multimodal color distributions, we train our model to predict per-pixel color histograms. This intermediate output can be used to automatically generate a color image, or further manipulated prior to image formation. On both fully and partially automatic colorization tasks, we outperform existing methods. We also explore colorization as a vehicle for self-supervised visual representation learning.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles2016
- Colorful Image Colorization2016
- Reconstructive Sparse Code Transfer for Contour Detection and Semantic Labeling2015
- $N^4$-Fields: Neural Network Nearest Neighbor Fields for Image Transforms2015
- The SUN Attribute Database: Beyond Categories for Deeper Scene UnderstandingInternational Journal of Computer Vision, 2014
- Probabilistic Joint Image Segmentation and Labeling by Figure-Ground CompositionInternational Journal of Computer Vision, 2013
- SUN database: Large-scale scene recognition from abbey to zoo2010
- A fast local descriptor for dense matching2008
- Automatic Image Colorization Via Multimodal Predictions2008
- Local Color Transfer via Probabilistic Segmentation by Expectation-Maximization2005