Digital Costume Model Generation from Graphic Narrative Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cosplay enthusiasts face challenges in creating accurate, high-quality costumes of their favorite characters from graphic narratives, and there is a lack of customizable commercially available costumes and delayed fulfillment of new costume demands.
Innovation Solution
A method and system for generating a digital costume model based on images from a digital graphic narrative using machine-learning models, allowing for customization, virtual try-on, and production of physical costumes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If commercially available costumes are produced for popular characters, then costume availability is improved, but customization capability deteriorates
Solution Approach 1:
The costume is divided into multiple interchangeable modular components (tops, bottoms, accessories, etc.) that can be independently selected and combined. Each module can be customized while maintaining overall costume coherence, resolving the contradiction between mass production availability and individual customization needs.
Solution Approach 2:
The costume system transitions from static pre-made designs to dynamic reconfigurable assemblies. Users can dynamically adjust and reconfigure costume elements based on their preferences, allowing commercially produced base designs to adapt to individual customization requirements.
2Adaptability or versatility
If custom costumes are created individually, then customization capability is improved, but production time deteriorates
Solution Approach 1:
Base costume designs and modular components are pre-produced and prepared in advance through automated manufacturing processes. When customization is needed, users simply select from pre-available options rather than creating from scratch, maintaining high customization while dramatically reducing production time.
Solution Approach 2:
The costume system uses universal modular components that can serve multiple characters and styles. The same base modules can be reconfigured for different characters, allowing rapid customization without requiring entirely new production cycles for each design.
3Manufacturing precision
If detailed costume elements are replicated, then costume accuracy is improved, but manufacturing complexity deteriorates
Solution Approach 1:
Original costume designs from graphic narratives are digitally copied and replicated using automated manufacturing processes. Digital patterns and specifications are reproduced with high precision through computer-controlled cutting and assembly, achieving accurate replication without manual craftsmanship complexity.
Solution Approach 2:
Traditional manual tailoring and crafting processes are replaced with automated mechanical and digital manufacturing systems. Computer-controlled cutting machines, 3D printing, and automated assembly replace hand-sewing and manual detailing, maintaining high accuracy while reducing manufacturing complexity and labor requirements.
Data Source
AI summary
A system and method are provided for generating a costume corresponding to graphic narrative (e.g., based, in part, on costumes depicted in images of a digital graphic narrative). Panels of the digital graphic narrative are segmented into elements (e.g., using semantic segmentation models like Fully Convolutional Networks), and clothing elements are identified as outfits/costumes worn by the characters. Based on multiple viewing angles provided by a plurality of images, data such as color and texture of the outfits/costumes is extracted and a digital costume model is created. The digital costume model can include animated and real-life components for rendering realistic and animated representations of the digital costume model. The digital costume model can be customized, shared on social media, used to help render a virtual environment, and used to fabricate a physical costume.