3D Software

Meta launches “world’s largest” 3D Model Digital Twin Catalog for AI-driven research

Facebook’s parent firm Meta has launched its new Digital Twin Catalog (DTC), advertised as the world’s “largest and highest quality 3D object model dataset.”

The catalog was developed by Reality Labs Research, Meta’s virtual reality (VR) and augmented reality (AR) research unit. It features over 2,400 detailed 3D models of real-life objects, also known as “digital twins.” 

Designed to advance 3D reconstruction research for e-commerce and immersive reality applications, these models reportedly deliver millimeter-level accuracy, closely matching their physical counterparts.

The models, which span a range of everyday items like toys and kitchen utensils, were captured using a 3D scanning rig from Covision Media. Researchers can now access the DTC to train, evaluate, and fine-tune artificial intelligence (AI) and machine learning-based reconstruction techniques. Meta hopes this will increase the readiness of virtual reconstruction for real-world applications.

Meta has also announced a new partnership with the e-commerce platform Shopify to advance research into object reconstruction. This collaboration seeks to bridge the gap between the complexities and costs associated with 3D model creation for digital products. 

The companies hope to make 7,000 additional digital twins available through a new academic competition targeting improved reconstruction algorithms.         

“By teaming up, we aim to make high-quality 3D digital assets more accessible and easier to create for entrepreneurs,” commented Shopify 3D support project lead Matt Koenig. “This initiative is one of many collaborations designed to enhance the capabilities of our platform and empower our merchants to better engage their customers.” 

3D models in Meta's Digital Twin Catalog. Image via Meta.
3D models in Meta’s Digital Twin Catalog. Image via Meta.

Meta to advance 3D model creation    

3D reconstruction generates detailed 3D models of real-world objects or scenes from 2D images or video footage. 

This technique is a major focus in computer vision research. However, the development of large-scale 3D model datasets within the academic community has been hindered by the significant costs associated with their creation.

Additionally, although datasets have expanded in recent years, many still lack sufficient geometric and material realism. According to Meta, few of these datasets include models linked to physical, real-world objects. Through its new DTC, the company aims to make 3D reconstruction techniques more robust and efficient.

In addition to the 2,400 3D models, the DTC also contains 2D recordings for a subset of the objects. These were captured using a traditional DSLR camera and Meta’s Project Aria research glasses. These resources aim to help researchers improve reconstruction for camera and smart glasses capture applications. 

Most 3D objects in the database have real-world counterparts that can be purchased from vendors. This enables researchers to acquire the original objects and conduct data capture experiments.

Meta ultimately aims for the new DTC to accelerate the expansion of 3D reconstruction and digital twins into e-commerce and immersive reality applications.

The company envisions a future where independent store owners and vendors can instantly convert their products into interactive 3D models using 2D images. These digital twins could then be accessed by potential customers shopping in augmented reality storefronts via AR headsets or smart glasses. Shoppers could project the models into their homes to see if the product would be a good fit in real life.

Through Meta’s new partnership with Shopify, furniture merchant Arhaus Furniture agreed to participate in the research efforts. The vendor hopes to see a commercial DTC-related platform in the future. 

“In an industry where experiencing products in person can be prohibitive, this collaboration allows us to bridge the gap with cutting-edge technology, bringing our physical pieces into the digital realm,” commented Steve Bauer, senior vice president of e-commerce and digital at Arhaus. 

“We believe 3D technology has a valuable place in the future of the home furnishings industry, which is why we’re excited to be partnering with Meta.”

Arhaus Furniture digital twin. Image via Meta.
An Arhaus Furniture digital twin. Image via Meta.

How important is this news? Take 15 seconds to tell us, make sure you click submit!

Digital recreation bolsters additive manufacturing 

Meta is not the first global tech company to advance digital recreation. In 2021, Google Arts & Culture partnered with the London-based cultural heritage project Scan the World. This collaboration sought to expand the availability of open-source, 3D printable art.  

Founded by Jonathan Beck in 2014, the Scan the World project uses 3D scanning technology to digitize culturally significant sculptures from around the world. These 3D models are then made freely available to the 3D printing community, educators, and other artists. 

The partnership with Google sought to further expand this collection, making museum objects on its Arts & Culture platform viewable in 3D. STL files are also available to download via Scan the World on MyMiniFactory’s website, making the models freely available for 3D printing.

Elsewhere, the wider manufacturing sector has witnessed increased adoption of digital twin technology over recent years. This has been driven by efforts to digitize inventories, reduce storage costs, and localize supply chains. 

It is not hard to see the potential application crossover between Meta’s new 3D reconstruction database and efforts to grow distributed manufacturing, localize 3D printing, and create the “factory of the future.”

In a project similar to the DTC, French software start-up Spare Parts 3D (SP3D) launched the beta program of Théia. Unveiled earlier this year, the new digital tool can automatically create 3D models from 2D technical drawings

Integrating the company’s AI-driven DigiPart software, Théia leverages deep learning technology to create 3D printable models of spare parts, reducing conversion times from days to minutes. 

SP3D claims that this new tool reduces the cost of digitization. This will reportedly allow more companies to adopt additive manufacturing to produce spares, reducing physical inventory costs. According to its developers, Théia can collectively save companies $34 billion a year through inventory digitization.   

German railway firm Deutsche Bahn (DB) possesses one of the largest digital inventories of 3D printable spare parts. The train manufacturer partnered with Berlin-based 3D printing software developer 3YOURMIND to create a ‘digital warehouse’ of parts. This has reportedly allowed DB to achieve significant time savings and reduce vehicle downtime.   

Manufacturing technology company Hexagon recently launched Digital Factory. The new offering allows companies to create digital replicas of their factories and add digital twins of machine hardware to a simulated shop floor. 

The company claims this will allow manufacturers to optimize their floor plans, pivot production lines, and create more sustainable future factories. Hexagon believes Digital Factory could save global manufacturing companies £35 million per year by avoiding costly mistakes when planning factory floor plans. Additionally, digitizing the factory floor could minimize on-site staff training requirements, reducing travel costs by 50%.         

Nominations are now open for the 2024 3D Printing Industry Awards

What does the future of 3D printing hold?

What near-term 3D printing trends have been highlighted by industry experts? 

Subscribe to the 3D Printing Industry newsletter to keep up with the latest 3D printing news.
 
You can also follow us on Twitter, like our  Facebook page, and subscribe to the 3D Printing Industry Youtube channel to access more exclusive content.

Featured image shows 3D models in Meta’s Digital Twin Catalog. Image via Meta.

© Copyright 2017 | All Rights Reserved | 3D Printing Industry