Nvidia’s latest AI transforms photographs into 3D scenes in seconds.

Instant NeRF is an advancement over NeRF, or neural radiance field, which is used to create realistic 3D sceneries from a set of 2D photos. According to Nvidia, their technology can learn a high-resolution 3D scene in seconds and produce pictures of that scene in milliseconds. The new capability was shown by the business at Nvidia GTC, a global conference for AI developers.

The Nvidia CUDA Toolkit and the Tiny CUDA Neural Networks library were used to create the technology. According to Nvidia, Instant NeRF might be as essential to 3D photography as digital cameras and JPEG compression have been to 2D photography. It feeds on “a few dozen still photographs” of the item, as well as data on the camera angles from which these shots were obtained.