Train Physical AI With Real-World Simulations Using fVDB.

21 930

13.6

NVIDIA1.79 млн

Следующее

145 дней – 4 981 28259:26

What’s Next in AI: NVIDIA’s Jensen Huang Talks With WIRED’s Lauren Goode

Популярные

310 дней – 53 5412:08

Eos: The Supercomputer Powering NVIDIA AI's Breakthroughs

05.07.23 – 5 1311:38

Live Graphics Production with Vizrt - NVIDIA M&E Partner Showcase

Опубликовано 29 июля 2024, 23:07

For physical AI to operate in 3D spaces, it must have spatial intelligence—the ability to understand and reason in the real world. Achieving spatial intelligence involves converting the world around us into AI-ready virtual representations that the model can understand. fVDB, developed by NVIDIA, is an open-source deep learning framework for sparse, large-scale, high-performance spatial intelligence. It builds NVIDIA-accelerated AI operators on top of OpenVDB to enable reality-scale simulations for training physical AI.

Read the full blog: blogs.nvidia.com/blog/fvdb-big...

Read the fVDB technical blog: developer.nvidia.com/blog/buil...

Watch: Introducing fVDB: Deep Learning Framework for Generative Physical AI with Spatial Intelligence youtube.com/watch?v=6JCp0hXb3S...

Apply for the fVDB Early Access Program: developer.nvidia.com/fvdb/earl...

Check out the OpenVDB Github: github.com/AcademySoftwareFoun...

Learn more about fVDB: developer.nvidia.com/fvdb

Свежие видео