Learning Diverse Image Colorization

Abstract

Colorization is an ambiguous problem, with multiple viable colorizations for a single grey-level image. However, previous methods only produce the single most probable colorization. Our goal is to model the diversity intrinsic to the problem of colorization and produce multiple colorizations that display long-scale spatial co-ordination. We learn a low dimensional embedding of color fields using a variational autoencoder (VAE). We construct loss terms for the VAE decoder that avoid blurry outputs and take into account the uneven distribution of pixel colors. Finally, we build a conditional model for the multi-modal distribution between grey-level image and the color field embeddings. Samples from this conditional model result in diverse colorization. We demonstrate that our method obtains better diverse colorizations than a standard conditional variational autoencoder (CVAE) model, as well as a recently proposed conditional generative adversarial network (cGAN).

This revision to appear in CVPR17

References in corpus (5)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• DRAW: A Recurrent Neural Network For Image Generation
• Deep Convolutional Inverse Graphics Network
• Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks
• Learning Representations for Automatic Colorization

Cited by in corpus (5)

• Unsupervised Diverse Colorization via Generative Adversarial Networks
• Detecting Anomalous Faces with 'No Peeking' Autoencoders
• On the Diversity of Realistic Image Synthesis
• Fully Automatic Video Colorization with Self-Regularization and Diversity
• Deep Nonparametric Estimation of Discrete Conditional Distributions via Smoothed Dyadic Partitioning