The next breakthrough to take the AI world by storm might be 3D model generators. This week, OpenAI open sourced Point-E, a machine learning system that creates a 3D object given a text prompt.

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. Neuralangelo ...

A neural field network can create a continuous 3D model from a limited number of 2D images, and it does it without being trained on other samples. Researchers from the McKelvey School of Engineering ...

If you buy something from a Verge link, Vox Media may earn a commission. See our ethics statement. is a senior reporter who has covered AI, robotics, and more for eight years at The Verge. Nvidia’s ...

Midjourney has this week released more details about new features it’s development team will soon be rolling out to users worldwide. These new Midjourney version 6 updates, including a significant ...

A few do's and don'ts speed the transition from 2D drawing to 3D modeling. Developers of 3D software say 70% or more of all designers and engineers still work in 2D. That's despite many advantages to ...

On Tuesday, Tencent released HunyuanWorld-Voyager, a new open-weights AI model that generates 3D-consistent video sequences from a single image, allowing users to pilot a camera path to "explore" ...

What if you could take a simple 2D image—a sketch, a logo, or even a photograph—and transform it into a fully realized 3D model, ready for 3D printing or digital design? For years, this process ...