Name
Title | ||
|---|---|---|
Discovering Density-Preserving Latent Space Walks in GANs for Semantic Image Transformations |
Abstract | ||
|---|---|---|
ABSTRACTGenerative 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. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1145/3474085.3475293 | International Multimedia Conference |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guanyue Li | 1 | 1 | 1.64 |
| Yi Liu | 2 | 82 | 29.92 |
| Xiwen Wei | 3 | 0 | 1.01 |
| Yang Zhang | 4 | 0 | 0.34 |
| Si Wu | 5 | 17 | 7.03 |
| Yong Xu | 6 | 37 | 6.30 |
| Hau-San Wong | 7 | 1008 | 86.89 |