Discovering Density-Preserving Latent Space Walks in GANs for Semantic Image Transformations

Guanyue Li, Yi Liu, Xiwen Wei, Yang Zhang, Si Wu, Yong Xu, Hau-San Wong

Abstract

Generative adversarial network (GAN)-based models possess superior capability of high-fidelity image synthesis. There are a wide range of semantically meaningful directions in the latent representation space of well-trained GANs, and the corresponding latent space walks are meaningful for semantic controllability in the synthesized images. To explore the underlying organization of a latent space, we propose an unsupervised Density-Preserving Latent Semantics Exploration model (DP-LaSE). The important latent directions are determined by maximizing the variations in intermediate features, while the correlation between the directions is minimized. Considering that latent codes are sampled from a prior distribution, we adopt a density-preserving regularization approach to ensure latent space walks are maintained in iso-density regions, since moving to a higher/lower density region tends to cause unexpected transformations. To further refine semantics-specific transformations, we perform subspace learning over intermediate feature channels, such that the transformations are limited to the most relevant subspaces. Extensive experiments on a variety of benchmark datasets demonstrate that DP-LaSE is able to discover interpretable latent space walks, and specific properties of synthesized images can thus be precisely controlled.
BibTeX
@inproceedings{li2021discovering,
  author = {Guanyue Li and Yi Liu and Xiwen Wei and Yang Zhang and Si Wu and Yong Xu and Hau-San Wong},
  title = {{Discovering Density-Preserving Latent Space Walks in GANs for Semantic Image Transformations}},
  booktitle = {ACM Multimedia},
  year = {2021},
  doi = {10.1145/3474085.3475293},
}

Loading related content...

Figure