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

Peiye Zhuang, Oluwasanmi O Koyejo, Alex Schwing

Keywords: Image manipulation, GANs, latent space of GANs

Abstract: 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.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We propose a state-of-the-art approach to semantically edit images by transferring latent vectors towards meaningful latent space directions.

Data: [CelebA-HQ](https://paperswithcode.com/dataset/celeba-hq), [FFHQ](https://paperswithcode.com/dataset/ffhq), [Places](https://paperswithcode.com/dataset/places)

Code: [ KelestZ/Latent2im](https://github.com/KelestZ/Latent2im) + [ 1 community implementation](https://paperswithcode.com/paper/?openreview=HOFxeCutxZR)