Get the latest tech news

Meta’s VFusion3D: A leap forward in AI-powered 3D content creation

Meta's VFusion3D AI breakthrough transforms 2D images into high-quality 3D models, revolutionizing content creation for VR, gaming, and design industries.

Junlin Han, Filippos Kokkinos, and Philip Torr led the research team in tackling a longstanding challenge in AI — the scarcity of 3D training data compared to the vast amounts of 2D images and text available online. The interface is straightforward, allowing users to either upload their own images or choose from a selection of pre-loaded examples, including iconic characters like Pikachu and Darth Vader, as well as more whimsical options like a pig wearing a backpack. This could democratize 3D content creation, allowing individuals and small teams to produce high-quality 3D assets at a scale previously only possible for large studios with significant resources.

Get the Android app