Shape-aware Generative Adversarial Networks for Attribute Transfer

TL;DR

This paper introduces a shape-aware GAN that effectively transfers visual attributes between images with different shapes, improving visual quality and shape preservation in image-to-image translation tasks.

Contribution

The paper proposes a novel shape-aware GAN model that maintains shape information during attribute transfer, enhancing the realism of generated images across diverse domains.

Findings

Produces more visually appealing images

Maintains shape integrity during transfer

Outperforms existing GAN-based translation models

Abstract

Generative adversarial networks (GANs) have been successfully applied to transfer visual attributes in many domains, including that of human face images. This success is partly attributable to the facts that human faces have similar shapes and the positions of eyes, noses, and mouths are fixed among different people. Attribute transfer is more challenging when the source and target domain share different shapes. In this paper, we introduce a shape-aware GAN model that is able to preserve shape when transferring attributes, and propose its application to some real-world domains. Compared to other state-of-art GANs-based image-to-image translation models, the model we propose is able to generate more visually appealing results while maintaining the quality of results from transfer learning.