Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation
This work improves image editing tools for users by enabling more precise and realistic attribute changes, though it is incremental as it builds on existing GAN-based approaches.
The paper tackles the problem of controllable semantic image editing using GANs, addressing issues like entangled attribute edits and loss of image identity, and achieves state-of-the-art performance in preserving realism and identity during transformations.
Controllable semantic image editing enables a user to change entire image attributes with a 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 that are entangled, global image identity changes, and diminished photo-realism. To address these concerns, we learn multiple attribute transformations simultaneously, integrate attribute regression into the training of transformation functions, and apply a content loss and an adversarial loss that encourages the maintenance of image identity and photo-realism. 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 preserving image identity and realism during transformation. We provide empirical results for both natural and synthetic images, highlighting that our model achieves state-of-the-art performance for targeted image manipulation.