Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation

Controllable semantic image editing enables a user to change entire image attributes with few clicks, e.g., gradually making a summer scene look like it was taken in winter. Classic approaches for this task use a Generative Adversarial Net (GAN) to learn a latent space and suitable latent-space transformations. However, current approaches often suffer from attribute edits which are entangled, global image identity changes, and diminished photo-realism. To address these concerns, we learn multiple attribute transformations simultaneously, we integrate attribute regression into the training of transformation functions, apply a content loss and an adversarial loss that encourage the maintenance of image identity and photo-realism. Beyond global transformations, we explore local edits that can succeed in failure cases of global directions. We propose quantitative evaluation strategies for measuring controllable editing performance, unlike prior work which primarily focuses on qualitative evaluation. Our model permits better control for both single- and multiple-attribute editing, while also preserving image identity and realism during transformation. We provide empirical results for both real and synthetic images, highlighting that our model achieves state-of-the-art performance for targeted image manipulation.