DraGAN

DragGAN Overview

DragGAN is a powerful tool for controlling generative adversarial networks (GANs) in a user-interactive manner. It allows users to "drag" any points of an image to precisely reach target points, providing flexible and precise controllability of the pose, shape, expression, and layout of the generated objects. DragGAN consists of two main components: a feature-based motion supervision and a new point tracking approach. It enables anyone to deform an image with precise control over where pixels go, manipulating diverse categories such as animals, cars, humans, landscapes, etc. The tool produces realistic outputs even for challenging scenarios such as hallucinating occluded content and deforming shapes that consistently follow the object's rigidity.

DragGAN Highlights

• DragGAN provides a powerful yet less explored way of controlling GANs, allowing users to "drag" any points of the image to precisely reach target points.
• It consists of two main components: a feature-based motion supervision that drives the handle point to move towards the target position, and a new point tracking approach that leverages the discriminative GAN features to keep localizing the position of the handle points.
• Through DragGAN, anyone can deform an image with precise control over where pixels go, thus manipulating the pose, shape, expression, and layout of diverse categories such as animals, cars, humans, landscapes, etc.