Meta Updates Its Horizon Hyperscape with 3D World Capture

Two months after its launch, Meta Platforms is overhauling its Horizon Hyperscape Capture app, moving the rendering process from the cloud to on-device for lower latency and mobility. Hyperscape Capture, unveiled at Meta Connect in September, lets you use a Meta Quest 3 or Quest 3S headset to scan and generate a real-world 3D environment — like your office or living room — to share as a photorealistic VR replica. Rather than cloud-rendered captures that were accessible solely within the app, Hyperscape Capture can now generate a Hyperscape as a Horizon Worlds destination — with audio. Continue reading Meta Updates Its Horizon Hyperscape with 3D World Capture

Mark Zuckerberg Unveils SAM 2 AI Tech for Segmenting Video

Meta Platforms CEO Mark Zuckerberg unveiled the latest version of computer vision platform SAM 2, an update on the company’s Segment Anything Model that automates for video what the original SAM did for still images — identifying the edges of an object and isolating it in the frame. Zuckerberg demonstrated SAM 2 as part of a SIGGRAPH 2024 keynote session in which he was interviewed by Nvidia CEO Jensen Huang. “Being able to do this in video and have it be zero shot and tell it what you want, it’s pretty cool,” Zuckerberg said. Meta is sharing the code and model weights for SAM 2 with a permissive Apache 2.0 license. Continue reading Mark Zuckerberg Unveils SAM 2 AI Tech for Segmenting Video

New Meta AI Can Detect Objects It Has Not Been Trained On

Meta Platforms has published a new AI technology, the Segment Anything Model (SAM) that the company claims can identify objects it hasn’t seen before. Acting on a text prompt, SAM will highlight items in a photo or video, picking out all the cats, for instance, or flowers. It can also execute other functions, such as generating a 3D construct using a single 2D image or extrapolating from things viewed in a mixed reality headset. Segment Anything can work in concert with other models, potentially minimizing the need for voluminous data sets for training. Continue reading New Meta AI Can Detect Objects It Has Not Been Trained On