The company just showed off an AI called Neural Radiance Field, or Instant NeRF, as illustrated in an official Nvidia blog post. Instant NeRF uses advanced algorithms to transform 2D photos into fully 3D objects, and it only takes “tens of milliseconds” to produce results. The tech can interpolate any visual information the 2D images did not capture, such as relative depth, creating a 3D object in the blink of an eye. Nvidia has been working on this AI for a while, but the speed of Instant NeRF is a newly announced concept, as older workups took much longer. The company sees a multitude of uses for Instant NeRF, from training robots to helping autonomous driving systems understand space. Nvidia also envisions a future for the process in gaming, entertainment, and architecture, among other fields. “Instant NeRF could be as important to 3D as digital cameras, and JPEG compression have been to 2D photography—vastly increasing the speed, ease, and reach of 3D capture and sharing,” says David Luebke, vice president for graphics research. Instant NeRF has been optimized to run on Nvidia GPUs, but the company says it works best on cards with tensor cores, so as to provide a bit of a performance boost for artificial intelligence algorithms. However, they have not announced if there is a consumer version on the horizon and what that would look like.
