Multimodal Image Outpainting With Regularized Normalized Diversification

TL;DR

This paper introduces a novel regularization technique and a feature pyramid discriminator to enhance diversity and quality in image outpainting, effectively addressing mode collapse in generative models.

Contribution

The paper proposes a new regularization method for diverse conditional image synthesis and a feature pyramid discriminator to improve image quality in outpainting tasks.

Findings

Produces more diverse images without quality loss

Outperforms state-of-the-art methods on CelebA and Cityscape datasets

Effectively mitigates mode collapse in generative models

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.