Multimodal Image Outpainting With Regularized Normalized Diversification

Abstract

In this paper, we study the problem of generating a set ofrealistic and diverse backgrounds when given only a smallforeground region. We refer to this task as image outpaint-ing. The technical challenge of this task is to synthesize notonly plausible but also diverse image outputs. Traditionalgenerative adversarial networks suffer from mode collapse.While recent approaches propose to maximize orpreserve the pairwise distance between generated sampleswith respect to their latent distance, they do not explicitlyprevent the diverse samples of different conditional inputsfrom collapsing. Therefore, we propose a new regulariza-tion method to encourage diverse sampling in conditionalsynthesis. In addition, we propose a feature pyramid dis-criminator to improve the image quality. Our experimen-tal results show that our model can produce more diverseimages without sacrificing visual quality compared to state-of-the-arts approaches in both the CelebA face dataset and the Cityscape scene dataset.

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Spectral Normalization for Generative Adversarial Networks
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• Adversarial Feature Learning
• Autoencoding beyond pixels using a learned similarity metric
• EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
• Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
• Context-Aware Synthesis and Placement of Object Instances