NVIDIA, one of the leading technology companies, continues to develop graphics technologies supported by artificial intelligence. The company, which introduced many technologies such as the technology that turns your doodles into a realistic scene as if you were drawing from Paint, this time showed its technology that brings a new definition to photography.
NVIDIA, with its newly developed technology called ‘Instant NeRF’, paved the way for making two-dimensional photos completely three-dimensional in just seconds. Moreover, the concept of three dimensions here is not created as planar like fake three-dimensional photographs, but as 360-degree viewable.
Photos become three-dimensional in minutes:
Instant NeRF, NVIDIA’s groundbreaking new technology, He transforms the subject into a three-dimensional object by examining his photographs taken from different angles with artificial intelligence. As seen in the video above, not only the subject, but also the environment in which the subject is located turns into a completely three-dimensional environment.
This technology developed by NVIDIA is not actually the first technology that enables two-dimensional photos to be converted into a three-dimensional scene. These up-to-date technologies called NeRF can also do the same. But the difference between the new Instant NeRF and NeRF is revealed in the completion time of this transaction. While standard technologies take a few hours to analyze the photo and render the scene, Instant NeRF reduces that time to just a few minutes.
In these few minutes, Instant NeRF analyzes photos while calculating angles, lighting, possible color changes in all directions, and more. Technology will bring many advantages such as making architectural designs in virtual worlds and enabling autonomous vehicles and robots to make more accurate measurements of real world objects.
The technology can be operated with NVIDIA graphics card as it makes use of NVIDIA’s CUDA Toolkit and CUDA Neural Networks. Especially on NVIDIA graphics cards with Tensor cores, the process is even faster.
Those who want to experience the technology can reach the official GitHub page by clicking this link.
31636
