This could be much-welcomed news for the coming Metaverse shift, spelling new opportunities and horizons for virtual object creation. Yes, ladies and gentlemen, we’re looking at a possible game-changer – today, Snap shared its latest research paper that outlines a new way to create 3D assets from photos and videos sourced from online collections, such as Google Images. Check out Snap’s official video.

The Virtual Labs

As explained in the video, Snap’s new process, which it calls ‘Neural Object Capture and Rendering from Online Image Collections’ (a mouthful), would get rid of the need for images to be photographed and rendered in a physical studio, which is currently one of the more time consuming and intensive aspects of current 3D object capture.

Instead, AR and VR creators would simply be able to search for an item on Google, select a group of relevant images, and the system would be able to fill in the gaps, enabling 3D object creation without the need for tedious scanning. Adding to the 3D aspect, objects must also be photographed at different angles.

As per Snap:

“This approach could unlock the ability for an AR creator or developer to digitize any object in the world, as long as there are photos or videos available of it found in an online image collection. This is a significant step towards the goal of creating a library of AR digital assets to overlay computing on the world.”

Given the rise of digital photography and Social Media posts, almost any object you can think of has been photographed many times, and from various angles. This means that, through this new process, anything could easily be transformed into a 3D virtual object, at least in theory. It could be a huge moment for Snap’s AR ambitions and layering objects over real-world scenes. Meanwhile, it could also lean into the coming Metaverse shift, where people will be able to create their own virtual environments which others can then visit and interact with.

Technology like this makes it easier to get into AR and VR. Up until now, Meta has been looking to advance its eCommerce to facilitate the expansion of its virtual item library, encouraging brands to scan in digital versions of their products to augment their in-app listings.

The Wrap

Through this process, combined with a certain level of automation, Meta, or anyone really, would be able to put together a huge collection of digital items, minus the need for someone else to input all the visual aspects. Snapchat will be presenting its paper at SIGGRAPH 2022, the premier conference for computer graphics and interactive techniques, which is also being held in Vancouver this week. It could be a valuable consideration that potentially boosts digital translation.

Subscribe to our ‘Bottoms Up!’ Newsletter. Get the latest social media blogs about news, updates, trends, and effective social media strategies to take your business to the highest level from Tristan Ahumada and Jeff Pfitzer.


Sources 

https://bit.ly/3PbdRQH