Automatic Digital Garment Initialization from Sewing Patterns (supplementary video)
The rapid advancement of digital fashion and generative AI technology calls for an automated approach to transform digital sewing patterns into well-fitted garments on human avatars. When given a sewing pattern with its associated sewing relationships, the primary challenge is to establish an initial arrangement of sewing pieces that is free from folding and intersections. This setup enables a physics-based simulator to seamlessly stitch them into a digital garment, avoiding undesirable local minima. To achieve this, we harness AI classification, heuristics, and numerical optimization. This has led to the development of an innovative hybrid system that minimizes the need for user intervention in the initialization of garment pieces. The seeding process of our system involves the training of a classification network for selecting seed pieces, followed by solving an optimization problem to determine their positions and shapes. Subsequently, an iterative selection-arrangement procedure automates the selection of pattern pieces and employs a phased initialization approach to mitigate local minima associated with numerical optimization. Our experiments confirm the reliability, efficiency, and scalability of our system when handling intricate garments with multiple layers and numerous pieces. According to our findings, 68 percent of garments can be initialized with zero user intervention, while the remaining garments can be easily corrected through user operations.
====================
ACM Transactions on Graphics (SIGGRAPH), 2024
Watch video Automatic Digital Garment Initialization from Sewing Patterns (supplementary video) online, duration hours minute second in high quality that is uploaded to the channel Yin Yang 27 May 2024. Share the link to the video on social media so that your subscribers and friends will also watch this video. This video clip has been viewed 57 times and liked it 1 visitors.
