Multimodal Image Outpainting With Regularized Normalized Diversification

Lingzhi Zhang, Jiancong Wang, Jianbo Shi; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 3433-3442

Abstract


In this paper, we study the problem of generating a set of realistic and diverse backgrounds when given only a small foreground region. We refer to this task as image outpainting. The technical challenge of this task is to synthesize not only plausible but also diverse image outputs. Traditional generative adversarial networks suffer from mode collapse. While recent approaches propose to maximize or preserve the pairwise distance between generated samples with respect to their latent distance, they do not explicitly prevent the diverse samples of different conditional inputs from collapsing. Therefore, we propose a new regularization method to encourage diverse sampling in this conditional synthesis. In addition, we propose a novel feature pyramid discriminator to improve the image quality. Our experimental results show that our model can produce more diverse images without sacrificing visual quality compared to state-of-the-arts approaches in both the CelebA face dataset and the Cityscape scene dataset.

Related Material


[pdf] [video]
[bibtex]
@InProceedings{Zhang_2020_WACV,
author = {Zhang, Lingzhi and Wang, Jiancong and Shi, Jianbo},
title = {Multimodal Image Outpainting With Regularized Normalized Diversification},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}