Stroke Synthesis Engine for Expressive Digital Art
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computer-based sketching systems face challenges in interpreting and recreating the nuances of human-drawn 3D or stylized 2D sketches, particularly when limited to 2DOF input, resulting in artificially stilted or less expressive strokes, as they lack the subtleties of real 6DOF input.
Innovation Solution
The system synthesizes high fidelity paintbrush strokes by using a library of pre-recorded 6DOF reference strokes to supplement lower dimension input data, constructing feature vectors, identifying nearest neighbors, and smoothing poses to generate a sequence of synthesized poses that follow the trajectory of the input stroke, effectively enhancing the expressiveness of strokes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If 2DOF input data is used for stroke generation, then device complexity is reduced and ease of operation is improved, but manufacturing precision and reliability of stroke quality deteriorate
Solution Approach 1:
The patent introduces an intermediary system (the stroke synthesis engine with reference library) that mediates between the simple 2DOF input and the desired high-quality 6DOF output. The reference library acts as a mediator containing pre-recorded high-fidelity stroke data that bridges the gap between limited input capabilities and high-quality output requirements, allowing 2DOF input to produce 6DOF output without requiring complex 6DOF input devices
Solution Approach 2:
The system changes the parameter dimensionality by synthesizing additional degrees of freedom from fewer input parameters. It transforms 2DOF or 3DOF input parameters into 6DOF output parameters by leveraging reference data and synthesis algorithms, effectively expanding the parameter space without requiring additional physical input dimensions
2Manufacturing precision
If 6DOF reference stroke data is used to supplement lower dimension input, then manufacturing precision and reliability of stroke quality are improved, but device complexity and loss of information are reduced
Solution Approach 1:
The patent applies preliminary action by pre-recording and storing 6DOF reference stroke data in a library before the actual stroke generation process. Artists create and record high-quality reference strokes in advance, which are then reused and referenced during normal operation, eliminating the need for complex real-time 6DOF input processing while maintaining high stroke quality
Solution Approach 2:
The system creates copies of high-fidelity 6DOF reference stroke data and uses these copies to supplement lower dimension input. Instead of requiring original 6DOF input devices, the system replicates the effects of 6DOF input by copying and adapting reference stroke characteristics to match the simplified input trajectory
3Ease of operation
If heuristics are used to compute dynamic 6DOF pose from 2DOF input, then ease of operation is maintained, but manufacturing precision and reliability of pose accuracy deteriorate
Solution Approach 1:
The reference library serves as an intermediary that provides accurate pose data corresponding to similar stroke trajectories. Instead of using crude heuristics, the system queries the reference library for poses that match the input trajectory characteristics, obtaining accurate pose information from pre-recorded high-quality data rather than computing it through approximate algorithms
Data Source
AI summary
Systems and methods for synthesizing paintbrush strokes may use high fidelity pose data of reference strokes to supplement lower dimension stroke data. For example, 6DOF data representing reference strokes created by skilled artists may be captured and stored in a library of reference strokes. A query stroke made by a less skilled artist/user and/or made using input devices that do not provide 6DOF data may be processed by a stroke synthesis engine to produce an output stroke that follows the trajectory of the query stroke and includes pose data from one or more reference strokes. The stroke synthesis engine may construct feature vectors for samples of reference strokes and query strokes, select the best neighbor feature vector from the library for each query stroke sample, assign the pose data of the best neighbor to the query sample, and smooth the sequence of assigned poses to produce the synthesized output stroke.