Image-to-Image Translation with Disentangled Latent Vectors for Face Editing
This work addresses targeted and controllable facial attribute editing for applications in computer vision, but it is incremental as it builds on existing latent space factorization techniques.
The paper tackles the problem of facial attribute editing in image-to-image translation by proposing a framework with disentangled latent vectors, achieving significant improvements over state-of-the-art methods.
We propose an image-to-image translation framework for facial attribute editing with disentangled interpretable latent directions. Facial attribute editing task faces the challenges of targeted attribute editing with controllable strength and disentanglement in the representations of attributes to preserve the other attributes during edits. For this goal, inspired by the latent space factorization works of fixed pretrained GANs, we design the attribute editing by latent space factorization, and for each attribute, we learn a linear direction that is orthogonal to the others. We train these directions with orthogonality constraints and disentanglement losses. To project images to semantically organized latent spaces, we set an encoder-decoder architecture with attention-based skip connections. We extensively compare with previous image translation algorithms and editing with pretrained GAN works. Our extensive experiments show that our method significantly improves over the state-of-the-arts.