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).

使用变分自编码器 (VAE) 建立灰度图像到多种可能颜色映射的条件模型，利用多模态分布的采样得到表现出长程空间协调性的多样性上色结果。与条件卷积变分自编码器（CVAE）和条件生成对抗网络（cGAN）方法相比，多模态变量 (VAE) 方法能够获得更好的多样性上色效果。