Stroke Prediction for Stylized Drawings Using Iterative Energy Minimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for creating stylized illustrations lack granular control and user interaction, requiring manual input and being unsuitable for novice users, while automated tools limit artistic freedom and are inefficient for interactive user systems.
Innovation Solution
An interactive drawing interface that generates stroke predictions based on prior strokes and a reference image using an iterative algorithm, allowing users to accept, ignore, or modify predictions for full control over the artistic process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated stroke generation algorithms are used, then productivity is improved, but ease of operation deteriorates due to loss of artistic control
Solution Approach 1:
The system implements feedback by allowing users to review generated stroke predictions and manually accept or reject them. This feedback loop enables users to maintain artistic control while benefiting from automated suggestions, resolving the contradiction between productivity improvement and ease of operation.
Solution Approach 2:
The system provides self-service by automatically generating stroke predictions based on learned user style and reference images, reducing manual effort. Users can accept these predictions with minimal interaction, improving productivity while maintaining control through selective acceptance.
2Manufacturing precision
If manual stroke input is required to preserve personal style, then ease of operation deteriorates, but manufacturing precision is improved
Solution Approach 1:
The system copies the user's personal drawing style by analyzing previously drawn strokes and learning stylistic patterns. It then generates new strokes that replicate this learned style, maintaining style consistency (manufacturing precision) without requiring manual input for each stroke, thus improving ease of operation.
Solution Approach 2:
The system performs preliminary action by pre-learning the user's drawing style from example strokes before actual drawing begins. This preliminary style acquisition enables automated stroke generation that matches personal style without requiring manual intervention during the drawing process.
3Ease of manufacture
If conventional texture stamp methods are used, then ease of manufacture is improved, but manufacturing precision deteriorates due to limited artistic control
Solution Approach 1:
The system changes parameters by dynamically adjusting stroke characteristics (thickness, opacity, curvature, spacing) based on the reference image content and learned user style. This enables high-quality, context-aware stroke generation that adapts to different drawing regions, improving manufacturing precision while maintaining ease of manufacture through automation.
Data Source
AI summary
Embodiments provide systems, methods, and computer storage media for generating stroke predictions based on prior strokes and a reference image. An interactive drawing interface can allow a user to sketch over, or with respect to, a reference image. A UI tool such as an autocomplete or workflow clone tool can access or identify a set of prior strokes and a target region, and stroke predictions can be generated using an iterative algorithm that minimizes an energy function considering stroke-to-stroke and image-patch-to-image-patch comparisons. For any particular future stroke, one or more stroke predictions may be initialized based on the set of prior strokes. Each initialized prediction can be improved by iteratively executing search and assignment steps to incrementally improve the prediction, and the best prediction can be selected and presented as a stroke prediction for the future stroke. The process can be repeated to predict any number of future strokes.