Nvidia predstavila novi AI algoritam koji može pretvoriti 2D slike u 3D objekte

Iako postoji puno aplikacija koje mogu 3D objekte „staviti“ u 2D perspektivu, vrlo malo ih je koji su u stanju napraviti suprotno. Pojednostavljeno, ako želite objekt u 3D-u, isti morate renderirati u 3D. Nakon toga, pretvaranje u 2D je poprilično jednostavan proces.

Koristeći slike ptica, AI je uspješno replicirao objekte iz više kuteva. Nastavno na to uspio je, poprilično uspješno, što je iznenadilo i same istraživače, rekreirati raznolike teksture.

Nvidijinu izjavu prenosimo u cijelosti:

“In traditional computer graphics, a pipeline renders a 3D model to a 2D screen. But there’s information to be gained from doing the opposite. A model that could infer a 3D object from a 2D image would be able to perform better object tracking, for example.

NVIDIA researchers wanted to build an architecture that could do this while integrating seamlessly with machine learning techniques. The result, DIB-R, produces high-fidelity rendering by using an encoder-decoder architecture. A type of neural network that transforms input into a feature map or vector that is used to predict specific information. Such as shape, color, texture and lighting of an image.

It’s especially useful when it comes to fields like robotics. For an autonomous robot to interact safely and efficiently with its environment, it must be able to sense and understand its surroundings. DIB-R could potentially improve those depth perception capabilities.”

Glavni zadatak nove DIB-R (differentiable interpolation-based renderer) tehnologije je mogućnost da proces koji je do nedavno zahtijevao nekoliko tjedana treniranja AI algoritama kako bi dobili „percepciju dubine“ objekata s kojim raspolažu sada smanjuje na nekoliko milisekundi.

Više detalja je dostupno na službenom Nvidia blogu.