New uses of 3D technology and AI in the fashion industry

When you’re purchasing a new item of clothing, you probably don’t think much about the design and assembly processes of the garment before you get to the store.

Creating a piece of apparel begins with a designer formulating an idea. A pattern is then created, fabric is selected and cut, and the garment is sewn. Finally the clothes are packed and sent.

To speed up the process, some apparel companies now use 3D technologies, including design software, body scanVisualization, and 3D printers. The tools allow designers to visualize their creations in different colors, fabrics, and motifs. known as incarnations digital twins These are created to simulate how clothes will look and fit on different body types. Body scans generate measurements for better-fitting clothing and better product design.

Some manufacturers incorporate artificial intelligence to streamline operations, and additional companies will likely explore it as it becomes more accurate.

However, not all apparel manufacturers are using 3D technologies to their full potential.

To advance 3D technology for designers, manufacturers and retailers 3D Retail Alliance Holds an annual challenge that highlights forward-looking academic institutions and startups. The competition is co-sponsored by IEEE Standards Association Industry Connections 3D Body Processing The program, which works with the textile industry to create standards for technology that uses 3D scanning to create digital models.

The winners of this year’s competition were selected in June PI Apparel Fashion Tech ShowHeld in New York City.

Fashion Institute of Technology (FIT) was awarded first position in the academic category. The New York City School offers programs in design, fashion, art, communications, and business.

pixascale Won the Startup category. Based in Herzogenaurach, Germany, the consultancy helps fashion and consumer goods companies automate content, manage 3D digital assets and improve workflows.

Custom-made clothes by 3D and AI

Poorly fitting clothing, shoes, and accessories are problems for clothing companies. average Return rates for clothes ordered online exceed 25 percent worldwideaccording to PrimeAI,

To create ready-to-wear clothes, designers use grading, a process that takes an initial sample pattern of a base size using established standards and a 3D body scan, then creates smaller and larger versions to mass produce. But the resulting clothes don’t fit everyone.

Returns, which can be frustrating for buyers, are costly for clothing companies because of reshipping and restocking expenses.

Some customers don’t bother to send back unwanted items, and they just throw them in the trash, where they eventually end up in landfills.

“What if we could go back to the days when you went to a shop, got measured, and someone custom made your garment?” Manati leigh lavengeAssistant Professor of Technical Design and Patternmaking at FIT.

This was the idea behind LaVange’s winning project, Automated Custom Sizing. Their proposal uses 3D technology and AI to create custom-tailored clothing on demand for all body types. In his presentation he outlined short and long term scalable solutions.

“I want to fix my fit problem, but I also realize that we can’t do that as an industry without changing the manufacturing process.” -Leigh LaVange

“I see it (custom sizing) as a solution that can be automated and eventually introduced across all different types of brands,” she says.

The short-term proposal involves measuring a person’s base physical specifications, such as bust, waist, thighs, biceps and hips – either manually or from a 3D body scan. An avatar of the customer is then created and entered into a database pre-loaded with 3D representations of different sizes of sample apparel. The AI ​​program notes the customer’s specifications and existing sizes to determine the best fit. If, for example, the person’s chest matches the dimensions of a medium size but the hips are a few millimeters larger, the program may still recommend a medium because it determined that the material around the hips had enough extra fabric. A rendering of an avatar wearing an item is shown to customers to help them decide whether to make a purchase.

LaVange says their solution will help improve customer satisfaction and reduce returns.

Their long-term planning is truly optimized. Using a 3D body scan, an AI program will determine the necessary adjustments to the pattern based on the customer’s specifications and important fit points such as the waist, while preserving the original design. The 3D system will then make changes, which will be presented on the customer’s avatar for approval. LaVange says the solution will eliminate excess inventory, since the clothes will be custom-made.

She says, because their proposals rely on technologies not currently used by the industry and a different way of interacting with customers, changes in production will be required.

“Most manufacturing systems today are set up to produce as many units as possible in a single day,” she says. “I believe there is a way to produce garments efficiently if you set up your manufacturing facility correctly. I want to fix my fit problem, but I also realize we can’t do that as an industry without changing the manufacturing process.”

A digital asset management platform

Winning submission in the Startup category, AI-First DAM (Digital Asset Management) as an Intelligent Backbone for Agile Product DevelopmentUses 3D technology and AI to combine clothing design components into one centralized platform.

Christian SonsPixascale’s chief executive launched the startup in February. he left Adidas in January after spending nine years at the company, where he was technical lead for digital manufacturing.

Sons says many apparel companies still store their 3D files on employees’ local drives or Microsoft’s share pointA web-based document-management system.

Those methods make things difficult because not everyone has access.

Sans’ cloud-based platform solves the problem by sharing digital assets such as images, videos, 3D models, base styles and documents for all parties involved in the process.

This includes designers, seamstresses and manufacturers. Their system integrates with the client’s file management system, providing access to the latest images, renderings, and other relevant data.

Their DAM system includes a library of embellishments like zippers and buttons, as well as fabric options.

“Bringing this information onto one platform where everyone can easily access and understand what others did really builds the foundation for collaboration.” -Christian Sons

“Bringing this information onto one platform where everyone can easily access and keep track of what others have done really builds the foundation for collaboration,” he says.

Sans is also working on incorporating AI agents and large language models to connect to internal systems and application programming interfaces to handle simple research requests autonomously.

Sons says this could include suggesting new products or different silhouettes, or revising last season’s offerings with new colors.

“These AI agents certainly won’t be perfect, but they’re a good starting point, so designers don’t have to start from scratch,” he says. “I think using AI agents is extremely exciting because for the last few years in the fashion industry, we’ve been talking about how AI will do the creative parts like designing a product. But now we’re talking about AI doing low-level tasks.”

A Display Information on how Pixascale’s DAM works is on YouTube.