Shape-aware Generative Adversarial Networks for Attribute Transfer
This addresses a problem in computer vision for applications requiring shape preservation during attribute transfer, representing an incremental improvement over existing GAN-based image-to-image translation models.
The paper tackles the challenge of attribute transfer between domains with different shapes by introducing a shape-aware GAN model, which generates more visually appealing results while maintaining transfer quality compared to state-of-the-art GAN-based methods.
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.