Nvidia’s 3D MoMa tool creates 3D models from 2D images using AI

According to Nvidia’s Vice President of Graphics Research, David Luebke, converting images into spatial models has long been considered the holy grail of computer vision and computer graphics. nvidia It appears that he has now approached the 3D rendering program MoMa. The tech giant promises that the AI-based tool should help architects, designers, artists, and other professionals to easily load things into their software.

The shape used for this is a grid of triangles as used in 3D design and games. Therefore, the format is compatible with commonly used editors and can be used for all kinds of post-load adjustments, such as scaling, distortion, texture and color adjustment.

The 3D model is made on the basis of images of the object in question. The material consists of a 2D image superimposed on the model, and the lighting depends on the images. With a single Tensor core in an Nvidia GPU, a model can be created in an hour.


The manufacturer demonstrates this with five different musical instruments, 100 photos of which were taken. In the joint video, it can be seen that they react to the light when it comes from a different angle. in paper”Extracting 3D models, materials and lighting from imagesMore details on running the program.

source:
hardware

« Previous Post Last Next »

See also  Ratchet & Clank: Rift Apart PC Benchmark with Nvidia GeForce

Winton Frazier

 "Amateur web lover. Incurable travel nerd. Beer evangelist. Thinker. Internet expert. Explorer. Gamer."

Leave a Reply

Your email address will not be published. Required fields are marked *