18419287. GENERATION OF STYLIZED DRAWING OF THREE-DIMENSIONAL SHAPES USING NEURAL NETWORKS simplified abstract (ADOBE INC.)
GENERATION OF STYLIZED DRAWING OF THREE-DIMENSIONAL SHAPES USING NEURAL NETWORKS
Organization Name
Inventor(s)
Aaron Hertzmann of San Francisco CA (US)
Matthew Fisher of Burlingame CA (US)
Evangelos Kalogerakis of Sunderland MA (US)
GENERATION OF STYLIZED DRAWING OF THREE-DIMENSIONAL SHAPES USING NEURAL NETWORKS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18419287 titled 'GENERATION OF STYLIZED DRAWING OF THREE-DIMENSIONAL SHAPES USING NEURAL NETWORKS
Simplified Explanation
The patent application describes techniques for generating stylized drawings of 3D shapes using neural networks. Here is a simplified explanation of the abstract:
- A processing device creates vector curve paths from a viewpoint of a 3D shape.
- A first neural network extracts surface geometry features of the 3D shape based on geometric properties of surface points.
- A second neural network determines predicted stroke attributes based on the surface geometry features and a predetermined drawing style.
- Based on the predicted stroke attributes, vector stroke paths are generated corresponding to the vector curve paths.
- A 2D stylized stroke drawing of the 3D shape is outputted based on the vector stroke paths.
- Potential Applications
This technology can be applied in various fields such as digital art, animation, virtual reality, and gaming for creating stylized 3D shapes and objects.
- Problems Solved
This technology solves the problem of efficiently generating stylized drawings of 3D shapes by automating the process using neural networks, reducing the manual effort required.
- Benefits
The benefits of this technology include faster creation of stylized drawings, consistency in style, and the ability to experiment with different drawing styles easily.
- Potential Commercial Applications
The technology can be commercialized in software applications for artists, designers, and developers working on projects that require stylized 3D drawings.
- Possible Prior Art
One possible prior art could be traditional methods of manually creating stylized drawings of 3D shapes, which are time-consuming and may lack consistency in style.
- Unanswered Questions
- How does this technology compare to existing software tools for creating stylized 3D drawings?
This article does not provide a direct comparison with existing software tools, so it is unclear how this technology stands out in terms of features, ease of use, and output quality.
- What are the limitations of using neural networks for generating stylized drawings of 3D shapes?
The article does not address any potential limitations or challenges that may arise when using neural networks for this purpose, such as training data requirements, computational resources, or potential biases in the generated drawings.
Original Abstract Submitted
Techniques for generating a stylized drawing of three-dimensional (3D) shapes using neural networks are disclosed. A processing device generates a set of vector curve paths from a viewpoint of a 3D shape; extracts, using a first neural network of a plurality of neural networks of a machine learning model, surface geometry features of the 3D shape based on geometric properties of surface points of the 3D shape; determines, using a second neural network of the plurality of neural networks of the machine learning model, a set of at least one predicted stroke attribute based on the surface geometry features and a predetermined drawing style; generates, based on the at least one predicted stroke attribute, a set of vector stroke paths corresponding to the set of vector curve paths; and outputs a two-dimensional (2D) stylized stroke drawing of the 3D shape based at least on the set of vector stroke paths.