Learning Representations for Automatic Colorization
Gustav Larsson, Michael Maire, Gregory Shakhnarovich · arXiv (Cornell University) · 2016
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.
Cited by 72 works. doi:10.48550/arxiv.1603.06668 Open-access PDF
Authors
References
- ImageNet Large Scale Visual Recognition Challenge
- Fully convolutional networks for semantic segmentation
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Normalized cuts and image segmentation
- Understanding the difficulty of training deep feedforward neural networks
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Learning Hierarchical Features for Scene Labeling
- SUN database: Large-scale scene recognition from abbey to zoo
- Context Encoders: Feature Learning by Inpainting
- ParseNet: Looking Wider to See Better