On the Diversity of Realistic Image Synthesis
arXiv:1712.07329
Abstract
Many image processing tasks can be formulated as translating images between two image domains, such as colorization, super resolution and conditional image synthesis. In most of these tasks, an input image may correspond to multiple outputs. However, current existing approaches only show very minor diversity of the outputs. In this paper, we present a novel approach to synthesize diverse realistic images corresponding to a semantic layout. We introduce a diversity loss objective, which maximizes the distance between synthesized image pairs and links the input noise to the semantic segments in the synthesized images. Thus, our approach can not only produce diverse images, but also allow users to manipulate the output images by adjusting the noise manually. Experimental results show that images synthesized by our approach are significantly more diverse than that of the current existing works and equipping our diversity loss does not degrade the reality of the base networks.
arXiv comment10 pages, 11 figures
References in corpus (12)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Conditional Image Synthesis With Auxiliary Classifier GANs
- NIPS 2016 Tutorial: Generative Adversarial Networks
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Autoencoding beyond pixels using a learned similarity metric
- Deep Photo Style Transfer
- Unsupervised Diverse Colorization via Generative Adversarial Networks
- Learning Diverse Image Colorization