Automated Artistic Image Creation via ML Stylization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital image editing applications lack functionality to significantly alleviate the efforts involved in creating artistic digital images, as they are limited to performing specific predefined actions and fail to provide substantial assistance in the creative process.
Innovation Solution
The implementation of machine learning-based models for fully automated or assisted digital image creation workflows, which apply a chosen visual style to source images or user-specified brush strokes, using a graphical user interface, and employ pre-processing, stylization, digital image analysis, and paint coating modules to generate and render artistic digital images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine learning-based models are implemented for automated digital image creation, then productivity is improved, but device complexity increases
Solution Approach 1:
The system is divided into distinct functional modules: a pre-processing module that prepares source images, a stylization module that applies visual styles using machine learning models, and a painting module that generates final artistic images. This segmentation allows complex image creation tasks to be handled by specialized subsystems working in sequence, improving overall productivity while managing system complexity through modular architecture.
2Ease of operation
If machine learning-based models are implemented for assisted digital image creation, then ease of operation is improved, but device complexity increases
Solution Approach 1:
The system introduces an intermediary processing layer between the user and the machine learning models. The pre-processing module receives user-provided source images and prepares them in a standardized format, while the painting module translates model outputs into final artistic images. This intermediary layer shields users from the complexity of machine learning operations, improving ease of operation while containing system complexity within the processing modules.
3Manufacturing precision
If visual styles are applied to source images or brush strokes, then manufacturing precision is improved, but loss of time increases
Solution Approach 1:
The pre-processing module performs preliminary preparation of source images before they are fed into the stylization module. By pre-processing images in advance (such as normalizing formats, extracting key features, or preparing canvas structures), the system reduces the computational burden during the actual stylization process, thereby maintaining high style application accuracy while reducing overall processing time.
Data Source
AI summary
An example method of automated creation of artistic digital images comprises: producing a styled digital image by performing stylization of a source digital image based on a specified visual style; identifying a plurality of visual elements of the styled digital image; generating a sequence of digital paint coat layers for the styled digital image, wherein each digital paint coat layer of the sequence of digital paint coat layers covers at least a subset of the plurality of visual elements of the styled digital image, and wherein each digital paint coat layer of the sequence of digital paint coat layers comprises a set of graphic primitives; and producing an output digital image by generating respective sets of graphic primitives of each digital paint coat layer of the plurality of digital paint coat layers, wherein the output digital image exhibits one or more visual features of the visual style.