Home > Technology peripherals > AI > AI can reconstruct crops from single photos of clothes

AI can reconstruct crops from single photos of clothes

WBOY
Release: 2023-12-03 08:39:41
forward
847 people have browsed it

According to a new study published on a preprint website, artificial intelligence (AI) can transform a single photo of a piece of clothing into a precise cutout to recreate the garment.

AI can reconstruct crops from single photos of clothes

Image source: "New Scientist" website

Garment manufacturing personnel need to make different shapes of material pieces according to the cutting drawings, use them as templates to cut and sew various fabrics, and finally integrate the various parts into a complete garment. Reversely reconstructing crop patterns from finished garments is a time-consuming task, but researchers at Singapore's Marine Artificial Intelligence Laboratory successfully achieved it by training an AI model using 1 million garment images and related crop patterns known to belong to the same garment. The original crop can be reconstructed with 95.7% accuracy from just a single photo of clothing

The researchers developed a two-stage AI system that analyzes never-before-seen images of clothing, figures out how to break them down into their component parts, and predicts where to stitch to form the garment.

Researchers say the first application of this technology will be in virtual reality, or virtual worlds, by digitally recreating the clothing people see and wear in real life. The researchers also hope that this artificial intelligence technology can be used in the real world, simply taking a picture of someone to help them further design clothing

No need to appear the original sentence, I can help you write some related content

The above is the detailed content of AI can reconstruct crops from single photos of clothes. For more information, please follow other related articles on the PHP Chinese website!

source:sohu.com
Statement of this Website
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
Popular Tutorials
More>
Latest Downloads
More>
Web Effects
Website Source Code
Website Materials
Front End Template