NVIDIA researchers have developed a new inverse rendering pipeline, NVIDIA 3D MoMa, that allows users to reconstruct a series of still photos into a 3D computer model of an object, or even a scene. The key benefit of this workflow, compared to more traditional photogrammetry methods, is its ability to output clean 3D models capable of being imported and edited out-of-the-box by 3D gaming and visual engines.
While there are other photogrammetry programs that will turn 2D images into 3D models, NVIDIA’s 3D MoMa technology takes it a step further by producing mesh, material and lighting information of the subjects and outputting it in a format that’s compatible with existing 3D graphics engines and modeling tools. And it’s all done in a relatively short timeframe, with NVIDIA saying 3D MoMa can generate triangle mesh models within an hour using a single NVIDIA Tensor Core GPU.
These five models were created using NVIDIA 3D MoMa. Credit: NVIDIA |
The model that’s output has three primary components: the 3D mesh model, the parameters for material(s) the object is made from and parameters about the lighting in the scene. This all-in-one output makes it easier to go from capture to implementation into the final product, be it for a video game or visual effects.
To showcase 3D MoMa and celebrate the rich jazz history in New Orleans, where the paper behind 3D MoMa will be presented at the Conference on Computer Vision and Pattern Recognition, NVIDIA captured around 100 images each of five jazz band instruments from different angles. The trumpet, trombone, saxophone, drum set and clarinet were then modeled using MoMa. You can see the results above.
Earlier this year, NVIDIA Research showed off Instant NeRF, which can turn 2D images into a 3D scene ‘in seconds.’ That’s not all, so far in 2022, we’ve also seen NVIDIA’s landmark achievement in neural graphics training and an impressive new NVIDIA Canvas update. There’s no doubt that AI offers some major benefits to creators, especially when it comes to saving time with creating artwork and models.
Author:
This article comes from DP Review and can be read on the original site.