GameWorks: Better Materials & Textures
Subscribe:  iCal  |  Google Calendar
Miami US   15, Jul — 20, Jul
Orlando US   24, Jul — 27, Jul
Grapevine US   25, Jul — 29, Jul
Los Angeles US   28, Jul — 29, Jul
Los Angeles US   28, Jul — 2, Aug
Latest comments
by Carlos Acevedo
41 min ago

I like the render quality, look very realistic and well integrated with the plate Physics are quite fucked up in that sim, the shuttle goes trough the building as if it was air, the shuttle should get totally designated by the impact Also the full simulation seems to go in slow motion while the cars and people moves on real time The ground destruction looks cool too, and the concept is interesting

by AmsberryLawFirm
2 hours ago

At The Amsberry Law Firm in San Antonio, we focus on helping our valued clients resolve legal concerns that have a profound impact on their lives and long-term well-being.

by Acacia hary
3 hours ago

This article is very detailed and meticulous, I have read many articles on this topic, but for this article, you leave me a deep impression and practical application to my life. Thank you for sharing.

GameWorks: Better Materials & Textures
7 March, 2017
NVIDIA is working on a ‘magical’ toolset, which helps to enchains textures, generate maps and creates organic variations of materials.

The technology is currently in beta, but you can sign-up to get an early look. The toolset is specifically targeted at 3d artists, who want to harness the full power of Deep Learning and NVIDIA CUDA. NVIDIA’s Developer Technologies & NVIDIA Research worked closely to develop tools which enhance games and graphics whilst speeding development times. This project has been going on for years now.

These tools allow developers and artists to use AI to automatically expand the variation of textures in their game; improve the image quality in games, and automatically generate textures and matching materials properties for real world objects from photographs.

When we showed these off, the highlight was a stunning demo that makes clear how machine learning can help accelerate the field of photogrammetry, in which DSLR photos are combined to create richly detailed 3D models of real-world objects.

It’s a case study of how GPUs — and the CUDA parallel computing platform and programming model — are powering machine learning applications for artists and engineers working across industries to create amazing experiences.


Technically this new technology could greatly improve the whole workflow and help you create realistic textures very fast. The technology could be used in a couple of ways right now. 


Allows the user to get a 2x or 4x increase in resolution of textures and photos.

Photo To Material: 2shot

Using two photos of a real-world surface, generates diffuse, normals, specular and gloss maps.





Texture Multiplier

Takes a texture or photo as input and provides the user with an organic variation.

So far we have very little details. Let’s hope we’ll be able to have a better look at this solution in the nearest future. Kind of reminds me a lot of the stuff Artomatix is doing right now. Looks absolutely amazing.



Leave a Reply

2 Comment threads
0 Thread replies
Most reacted comment
Hottest comment thread
2 Comment authors
Jane BudosSimon Che de Boer Recent comment authors
Jane Budos
Jane Budos

Check this out as well.
RealityCapture is cool! 🙂

Simon Che de Boer
Simon Che de Boer Download available of the MANA VR demo. Still BETA so be kind.