2022/07/07 by Yusuf Dalva, Dalva, Yusuf, Said Fahri Altindis +4 · 1 citation
Computer Science · #Advanced Image Processing Techniques #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face recognition and analysis #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #cs.AI #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2207.03411
ECCV 2022
arxiv created 2022/07/07 · openalex publication_date 2022/07/07 · arxiv updated 2022/07/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.