Sketch Video Generation Using Progressive Drawing Frames
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Ordinary users lack the artistic skills to create dynamic videos simulating the process of professional artists drawing pencil sketches, making it difficult for them to produce such videos.
Innovation Solution
A method and apparatus that generate a video simulating a painter creating a sketch image step by step, involving generating sketch images at different color depths and drawing completion degrees, and arranging frames based on color depth and completion degrees to create a sketch drawing video.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real videos of artists painting are used to simulate sketch creation, then the video authenticity and artistic quality are improved, but the accessibility and ease of use for ordinary users deteriorate
Solution Approach 1:
The patent creates synthetic sketch drawing videos by generating intermediate sketches through image processing algorithms rather than using real artist videos. It copies the visual appearance and progression of hand-drawn sketches by processing the target sketch image to extract line structures and generate sequential drawing frames, making the content accessible to ordinary users while maintaining visual authenticity
Solution Approach 2:
The patent replaces the mechanical system of actual artistic creation with an automated image processing system. By using computer algorithms to analyze the target sketch, extract line structures, generate intermediate sketches at different completion stages, and assemble them into a video sequence, it substitutes human artistic skill with automated image processing while achieving the same visual effect
2Reliability
If complex deep learning methods are used to generate sketch drawing videos, then the video quality and artistic effect are improved, but the computational complexity and processing time increase
Solution Approach 1:
The patent extracts only the essential line structure information from the target sketch image using simple image processing operations such as edge detection and thresholding. By taking out only the necessary structural elements rather than attempting to replicate the entire complex artistic creation process, it achieves efficient generation of intermediate sketches with acceptable video quality
Solution Approach 2:
The patent changes parameters of the target sketch image (such as threshold values, line width, and completion degree thresholds) to generate intermediate sketches with varying levels of detail. By adjusting these parameters, it produces a sequence of sketches representing different stages of drawing completion, enabling video generation without requiring complex deep learning models
Data Source
AI summary
A video generation method is provided. After a source image is acquired by an electronic device, sketch images of different stages in a process of simulating a painter to draw a target sketch are generated based on the source image in an order of color from light to dark, and a plurality of subgraphs in the process of simulating the painter to draw the sketch image are generated in an order of drawing completion degrees from low to high. Then, respective subgraphs of respective sketch images in the plurality of sketch images are taken as video frames of a sketch drawing video, an order of the video frames is set according to the order of color depth from light to dark and the order of drawing completion degrees from low to high.