Mpg

Synthesizing visual content that meets users' needs often requires flexible and precise controllability of the pose, shape, expression, and layout of the generated objects

0 Reviews

What is Mpg?

The study presents DragGAN, a novel method for interactive point-based manipulation of generative adversarial networks (GANs) to provide flexible and precise control over the pose, shape, expression, and layout of generated objects. Unlike existing approaches reliant on annotated data or prior 3D models, DragGAN enables users to "drag" points on an image to specific target positions interactively. This control is facilitated by a feature-based motion supervision guiding the handle point movement towards the target and a point tracking system based on discriminative GAN features. The method allows for manipulation of various categories like animals, cars, humans, and landscapes on the learned generative image manifold. Results indicate enhanced performance in image manipulation and point tracking compared to previous methods. Real image manipulation through GAN inversion is also demonstrated. The project is supported by various institutions and made available for non-commercial use under Creative Commons licensing. Further details can be accessed via the provided contact information.
Display image for Mpg

How To Use Mpg

  • Utilize the interactive point-based manipulation feature.
  • Explore different objects like Lion, Cat, Dog, Horse, Elephant, Face, Human, Car, Microscope, and Landscapes.
  • Download the paper and the code provided for further exploration.

Total Traffic For Mpg

Features

  • ⭐️ Pose, shape, expression, and layout controllability for generated objects.
  • ⭐️ Interactive point-based manipulation for flexibility.
  • ⭐️ Support for various objects including animals, humans, and inanimate objects.
  • ⭐️ User-friendly tools for visual content synthesis.
  • ⭐️ License for non-commercial use under Creative Commons CC BY-NC 4.0.
  • ⭐️ Acknowledged support from ERC Consolidator Grant 4DReply (770784).
  • ⭐️ Contact Xingang Pan for questions and clarifications.

Frequently asked questions

List Alternatives & Comparisons Here

Add Optional YouTube Video Here