Multimodal Image Outpainting with Regularized Normalized Diversification

Lingzhi Zhang, Jiancong Wang, Jianbo Shi
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
Figure 1 : Given only a small foreground region, our model can learn to outpaint a set of diverse and plausible missing backgrounds in both face image and street scene image. 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
more » ... ial networks suffer from mode collapse. While recent approaches [32, 28] 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 conditional synthesis. In addition, we propose a 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 stateof-the-arts approaches in both the CelebA face dataset [29] and the Cityscape scene dataset [2] . Code is available at: https://github.com/owenzlz/DiverseOutpaint
doi:10.1109/wacv45572.2020.9093636 dblp:conf/wacv/ZhangWS20a fatcat:4tiqyfsvvjclroesqugdbibsii