Hierarchical Semantic Regularization of Latent Spaces in StyleGANs

Abstract

Progress in GANs has enabled the generation of high-resolution photorealistic images of astonishing quality. StyleGANs allow for compelling attribute modification on such images via mathematical operations on the latent style vectors in the W/W+ space that effectively modulate the rich hierarchical representations of the generator. Such operations have recently been generalized beyond mere attribute swapping in the original StyleGAN paper to include interpolations. In spite of many significant improvements in StyleGANs, they are still seen to generate unnatural images. The quality of the generated images is predicated on two assumptions; (a) The richness of the hierarchical representations learnt by the generator, and, (b) The linearity and smoothness of the style spaces. In this work, we propose a Hierarchical Semantic Regularizer (HSR) which aligns the hierarchical representations learnt by the generator to corresponding powerful features learnt by pretrained networks on large amounts of data. HSR is shown to not only improve generator representations but also the linearity and smoothness of the latent style spaces, leading to the generation of more natural-looking style-edited images. To demonstrate improved linearity, we propose a novel metric - Attribute Linearity Score (ALS). A significant reduction in the generation of unnatural images is corroborated by improvement in the Perceptual Path Length (PPL) metric by 16.19% averaged across different standard datasets while simultaneously improving the linearity of attribute-change in the attribute editing tasks.

Video

Citation

If you find our work helpful in your research, please cite our work:

@InProceedings{karmali2022hierarchical,

author="Karmali, Tejan and Parihar, Rishubh and Agrawal, Susmit and Rangwani, Harsh and Jampani, Varun and Singh, Maneesh and Babu, R. Venkatesh",

title="Hierarchical Semantic Regularization of Latent Spaces in StyleGANs",

booktitle="Computer Vision -- ECCV 2022",

year="2022",

pages="443--459",

}

Licence

This project is licenced under an [MIT License].

Contact

If you have any queries, please get in touch via email: tejank10@gmail.com