VecGAN: Image-to-Image translation with interpretable latent directions

Date
2022-10-21
Editor(s)
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
Computer Vision – ECCV 2022
Print ISSN
03029743
Electronic ISSN
Publisher
Volume
13676
Issue
Pages
153 - 169
Language
English
Journal Title
Journal ISSN
Volume Title
Series
Abstract

We propose VecGAN, an image-to-image translation framework for facial attribute editing with interpretable latent directions. Facial attribute editing task faces the challenges of precise attribute editing with controllable strength and preservation of the other attributes of an image. For this goal, we design the attribute editing by latent space factorization and for each attribute, we learn a linear direction that is orthogonal to the others. The other component is the controllable strength of the change, a scalar value. In our framework, this scalar can be either sampled or encoded from a reference image by projection. Our work is inspired by the latent space factorization works of fixed pretrained GANs. However, while those models cannot be trained end-to-end and struggle to edit encoded images precisely, VecGAN is end-to-end trained for image translation task and successful at editing an attribute while preserving the others. Our extensive experiments show that VecGAN achieves significant improvements over state-of-the-arts for both local and global edits.

Course
Other identifiers
Book Title
Citation
Published Version (Please cite this version)