DraGan

DragGAN is an innovative tool that provides precise control over image manipulation by allowing users to 'drag' points in an image to desired positions. This enables flexible adjustments in pose, shape, expression, and layout of various objects such as animals, cars, and landscapes. Its feature-based motion supervision combined with a new point-tracking approach ensures realistic outputs even in complex scenarios. This functionality is especially valuable for creative professionals, researchers, and anyone needing high precision in visual content creation.

DragGAN is an interactive image manipulation technique that allows users to precisely control the pose, shape, expression, and layout of objects in images by dragging points to target positions. It operates on the generative manifold of a GAN, using feature-based motion supervision and a novel point-tracking approach to produce realistic outputs, even for occluded or rigid deformations. The method supports diverse categories such as animals, cars, humans, and landscapes, and can also be applied to real images via GAN inversion.