20230126250. Systems for Generating Digital Objects to Animate Sketches simplified abstract (ADOBE INC.)
Systems for Generating Digital Objects to Animate Sketches
Organization Name
Inventor(s)
Zeyu Wang of New Haven CT (US)
Yangtuanfeng Wang of London (GB)
Systems for Generating Digital Objects to Animate Sketches - A simplified explanation of the abstract
This abstract first appeared for US patent application 20230126250 titled 'Systems for Generating Digital Objects to Animate Sketches
Simplified Explanation
The patent application describes a system for generating animated digital objects based on user sketched input. The system uses a generative adversarial network to generate a digital object with a non-photorealistic style that matches the user's sketch. The system modifies the style based on a comparison between the user's style and the desired non-photorealistic style.
- The system receives input data describing a user sketched digital object with a pose and a non-photorealistic style.
- An encoder of a generative adversarial network generates a latent vector representation of the user defined non-photorealistic style.
- A generator of the generative adversarial network uses the latent vector representation to generate a digital object with the desired pose and non-photorealistic style.
- The system modifies the latent vector representation based on a comparison between the user defined non-photorealistic style and the desired non-photorealistic style.
Potential Applications
- Animation and gaming industry: This technology can be used to quickly generate animated digital objects with specific non-photorealistic styles, saving time and effort for animators and game developers.
- Virtual reality and augmented reality: The system can be used to generate digital objects with non-photorealistic styles that match the visual aesthetics of virtual and augmented reality environments.
Problems Solved
- Time-consuming manual creation of non-photorealistic digital objects: The system automates the process of generating digital objects with non-photorealistic styles, reducing the time and effort required by artists.
- Matching user-defined style: The system ensures that the generated digital objects accurately reflect the non-photorealistic style defined by the user, improving the quality and consistency of the output.
Benefits
- Efficiency: The system streamlines the process of generating digital objects with non-photorealistic styles, allowing artists to focus on other creative aspects.
- Customization: Users can define their desired non-photorealistic style, and the system will generate digital objects that match their preferences.
- Consistency: The system ensures that the generated digital objects maintain a consistent non-photorealistic style, improving the overall visual coherence of animations and games.
Original Abstract Submitted
in implementations of systems for generating digital objects to animate sketches, a computing device implements a sketch system to receive input data describing a user sketched digital object having a pose and a non-photorealistic style. the sketch system generates a latent vector representation of the user defined non-photorealistic style using an encoder of a generative adversarial network. a digital object is generated having the pose and a non-photorealistic style using a generator of the generative adversarial network based on the latent vector representation of the user defined non-photorealistic style. the sketch system modifies the latent vector representation of the user defined non-photorealistic style based on a comparison between the user defined non-photorealistic style and the non-photorealistic style.
