StabilityAI has built a new video model that turns an image of an object into a full 3D representation with ... This is a library of millions of annotated 3D objects used by a number of AI 3D ...

Roblox is launching and open-sourcing Cube 3D, the first version of its foundational AI model for generating 3D objects. The model is trained on 3D objects. Eventually, it will be multimodal.

Roblox announced Monday that it’s launching the first iteration of its 3D model, dubbed “Cube,” to allow creators to create 3D objects using generative AI.

We take hyper-realistic 3D scanned and rendered cars for granted today. They're in movies, video games, fake spy shots, everywhere. The fact that it can be done at all still feels like science ...

Apple said developers like Wayfair, Etsy and others are using Object Capture to create 3D models of real-world objects — an indication that online shopping is about to get a big AR upgrade.

NVIDIA has introduced a new AI model called Neuralangelo that can create 3D replicas of objects from 2D videos, whether they're classic sculptures or run-of-the-mill trucks and buildings.

This so-called Large Photogrammetry Model is able to reconstruct 3D objects and scenes from just a few 2D photos, but with a big difference from current pipelines. Here’s why this is a big deal ...

For more details about the new Object Capture API, check out the “Create 3D models with Object Capture” WWDC 2021 session. Add 9to5Mac to your Google News feed.

StabilityAI, makers of the Stable Diffusion family of AI image models has unveiled a new image-to-3D tool called TripoSR that can quickly turn a picture into an object. There are a growing number ...