What if you could instantly transform a 2D capture into a 3D scene?
That would be some pretty powerful (and useful) technology, especially if you make movies or video games. Well, NVIDIA just added that concept to their growing list of exploratory technologies, furthering both their credentials in the fields of innovation and pioneering new ways to interpret data for creative or scientific purposes. Called NeRF, the tech uses an approximation of “how light behaves in the real world, enabling researchers to reconstruct a 3D scene from a handful of 2D images taken at different angles.”
In a blog post on their website, vice president for graphics research at NVIDIA David Luebke explained that “If traditional 3D representations like polygonal meshes are akin to vector images, NeRFs are like bitmap images: they densely capture the way light radiates from an object or within a scene…In that sense, 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.”
Of course, all of this requires a lot of computing power and here, yet again, NVIDIA has developed a pretty amazing innovation. Because NeRF is optimized for their technology, NVIDIA has cut down the amount of time AI needs to “guess” about what it is looking at and is able to rely upon something known as multi-resolution hash grid encoding. The company is exploring how NeRF could be used in other fields as well as how it might help AI with deep learning tasks and improve its efficiency in other areas.
You can watch a YouTube video demonstrating the technology at this link right here.
We’d like to know your thoughts on NVIDIA’s technology in the comments below.
We’ve got some other photography news for you to read here at this link.