Synthesizing visual content that meets users' needs often requires flexible and precise controllability of the pose, shape, expression, and layout of the generated objects. Existing approaches gain controllability of generative adversarial networks (GANs) via manually annotated training data or a prior 3D model, which often lack flexibility, precision, and generality. In this work, we study a powerful yet much less explored way of controlling GANs, that is, to

Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold

แนะนำ

What is DragGAN?

DragGAN is a powerful tool for interactive point-based manipulation on the generative image manifold. It allows users to "drag" any points of the image to precisely reach target points in a user-interactive manner.

How does DragGAN work?

DragGAN consists of two main components: 1) a feature-based motion supervision that drives the handle point to move towards the target position, and 2) a new point tracking approach that leverages the discriminative GAN features to keep localizing the position of the handle points.

Features of DragGAN

  • Precise control over where pixels go, thus manipulating the pose, shape, expression, and layout of diverse categories such as animals, cars, humans, landscapes, etc.
  • Ability to deform an image with realistic outputs even for challenging scenarios such as hallucinating occluded content and deforming shapes that consistently follow the object's rigidity.
  • Can be used for image manipulation and point tracking tasks.

Price

The paper and code are available for free, and the images, text, and video files on the site are made freely available for non-commercial use under the Creative Commons CC BY-NC 4.0 license.

Drag - ทางเลือก

get started with soona’s AI tools & creative platform

Unlock the ultimate toolkit for professional + UGC content, managing product creativity, and measuring performance. Elevate your brand with our comprehensive suite for content creation, management, and analytics.

--
PikPoet | Bridges the gap between your photos and perfect captions.

Explore the world of creative expressions and make your pictures speak volumes with beautiful and evocative textual expressions

--
AI Image Editor

Advanced AI-powered tools for one-click image restoration, generative filling, object removal, recoloring, and background remove.

--
AI multi-style cartoon generator

This tool allows you to convert your preferred photos into cartoon images with manga, 3D, or freehand styles, offering versatile artistic transformations. It provides users with the ability to infuse different visual aesthetics into their favorite pictures, ranging from the dynamic and stylized manga look to the depth of 3D or the charm of freehand drawing.

--
แท็กเพิ่มเติมเกี่ยวกับ: Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold