2021 IEEE International Conference on Image Processing
19-22 September 2021 • Anchorage, Alaska, USA
Imaging Without Borders
| Paper ID | ARS-5.3 | ||
| Paper Title | MULTIPLE STYLE TRANSFER VIA VARIATIONAL AUTOENCODER | ||
| Authors | Zhi-Song Liu, Vicky Kalogeiton, Marie-Paule Cani, Ecole Polytechnique, CNRS (LIX), IP Paris, France | ||
| Session | ARS-5: Image and Video Synthesis, Rendering and Visualization | ||
| Location | Area I | ||
| Session Time: | Tuesday, 21 September, 08:00 - 09:30 | ||
| Presentation Time: | Tuesday, 21 September, 08:00 - 09:30 | ||
| Presentation | Poster | ||
| Topic | Image and Video Processing: Restoration and enhancement | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | Modern works on style transfer focus on transferring style from a single image. Recently, some approaches study multiple style transfer; these, however, are either too slow or fail to mix multiple styles. We propose ST-VAE, a Variational AutoEncoder for latent space-based style transfer. It performs multiple style transfer by projecting nonlinear styles to a linear latent space, and it fuses different styles by linear interpolation and transfer the new style to the content image. To evaluate ST-VAE, we present experiments on COCO for single and multiple style transfer. Moreover, we present a case study revealing that ST-VAE outperforms other methods while being faster, flexible, and setting a new path for multiple style transfer. The code, models and results will be made available | ||