Apple’s latest announcement at the Worldwide Developers Conference introduces a new AI feature for creating 3D images from 2D originals, enhancing the capabilities of Vision Pro goggles and the Vision OS 2 update. The innovative technology aims to revolutionise content creation for augmented reality devices.
Apple has announced a new AI-powered feature capable of generating 3D images from 2D originals, unveiled during the Worldwide Developers Conference (WWDC). These images are designed to be viewed on Apple’s Vision Pro goggles, as part of the Vision OS 2 update, which includes several enhancements to the operating system for these augmented reality devices.
Among the updates to the photos app is the SharePlay feature, which allows users to view photos simultaneously with friends who also own Vision Pro goggles. The generative AI technology used to create 3D images from 2D originals works by “filling in the blanks” for different viewpoints, an approach distinct from traditional methods that use binocular cameras. Apple claims this method brings memories to life with natural-looking depth and dimension.
The introduction of this AI feature is part of a broader push by Apple to enhance 3D content creation capabilities. Other updates announced at WWDC include tools from Canon and Blackmagic aimed at producing immersive video content. Additionally, Apple plans to bring editing tools for spatial video to Final Cut Pro later this year, enabling editing on Mac and viewing on Vision Pro.
These developments could influence how creatives approach content creation for augmented reality devices, balancing technical innovation with directorial vision.
