GAN-Control: Explicitly Controllable GANs
This work addresses the problem of achieving explicit and fine-grained control over GAN-generated images for researchers and practitioners working with image synthesis, offering a more versatile solution than existing methods.
This paper introduces a framework for training Generative Adversarial Networks (GANs) that allows explicit control over generated image attributes like age, pose, and expression. Unlike previous methods that offer partial control or rely on 3D face models, this approach achieves state-of-the-art performance qualitatively and quantitatively across human faces, painted portraits, and dog images.
We present a framework for training GANs with explicit control over generated images. We are able to control the generated image by settings exact attributes such as age, pose, expression, etc. Most approaches for editing GAN-generated images achieve partial control by leveraging the latent space disentanglement properties, obtained implicitly after standard GAN training. Such methods are able to change the relative intensity of certain attributes, but not explicitly set their values. Recently proposed methods, designed for explicit control over human faces, harness morphable 3D face models to allow fine-grained control capabilities in GANs. Unlike these methods, our control is not constrained to morphable 3D face model parameters and is extendable beyond the domain of human faces. Using contrastive learning, we obtain GANs with an explicitly disentangled latent space. This disentanglement is utilized to train control-encoders mapping human-interpretable inputs to suitable latent vectors, thus allowing explicit control. In the domain of human faces we demonstrate control over identity, age, pose, expression, hair color and illumination. We also demonstrate control capabilities of our framework in the domains of painted portraits and dog image generation. We demonstrate that our approach achieves state-of-the-art performance both qualitatively and quantitatively.