Multi-View Image Generation from a Single-View

TL;DR

This paper introduces VariGANs, a novel model that generates multi-view images of clothing from a single view by combining variational inference and GANs in a coarse-to-fine process, improving realism and detail.

Contribution

The paper proposes VariGANs, a new multi-view image generation model that effectively combines variational inference and GANs for more realistic clothing images from a single view.

Findings

Generated images are more plausible than existing methods.

The model produces images with richer and sharper details.

Global appearance consistency is improved.

Abstract

This paper addresses a challenging problem -- how to generate multi-view cloth images from only a single view input. To generate realistic-looking images with different views from the input, we propose a new image generation model termed VariGANs that combines the strengths of the variational inference and the Generative Adversarial Networks (GANs). Our proposed VariGANs model generates the target image in a coarse-to-fine manner instead of a single pass which suffers from severe artifacts. It first performs variational inference to model global appearance of the object (e.g., shape and color) and produce a coarse image with a different view. Conditioned on the generated low resolution images, it then proceeds to perform adversarial learning to fill details and generate images of consistent details with the input. Extensive experiments conducted on two clothing datasets, MVC and DeepFashion, have demonstrated that images of a novel view generated by our model are more plausible than those generated by existing approaches, in terms of more consistent global appearance as well as richer and sharper details.