NVIDIA brings advancements in Generative AI to SIGGRAPH 2023
By
NVIDIA brings advancements in Generative AI to SIGGRAPH 2023
NVIDIA is presenting 20 research papers at the computer graphics conference SIGGRAPH 2023 that highlight collaborations around generative AI and neural graphics that came from collaborations from over a dozen universities in the U.S., Europe, and Israel.
The research advancements presented this year at SIGGRAPH will help developers and enterprises rapidly generate synthetic data to populate virtual worlds for robotics and autonomous vehicle training. They’ll also enable creators in art, architecture, graphic design, game development and film to produce high-quality visuals for storyboarding, pre-visualisation and even production.
Innovations by NVIDIA researchers are regularly shared with developers on GitHub and incorporated into products, including the NVIDIA Omniverse platform for building and operating metaverse applications and NVIDIA Picasso, a recently announced foundry for custom generative AI models for visual design.
One paper describes a technique that needs a single example image to customise its output, accelerating the personalisation process from minutes to roughly 11 seconds on a single NVIDIA A100 Tensor Core GPU, more than 60x faster than previous personalisation approaches.
A second paper introduces a highly compact model called Perfusion, which takes a handful of concept images to allow users to combine multiple personalised elements — such as a specific teddy bear and teapot — into a single AI-generated visual.
A third paper showcases a method that can simulate tens of thousands of hairs in high resolution and in real-time using neural physics, an AI technique that teaches a neural network to predict how an object would move in the real world.
In another SIGGRAPH paper, NVIDIA will present neural texture compression that delivers up to 16x more texture detail without taking additional GPU memory. Neural texture compression can substantially increase the realism of 3D scenes, as seen in the image above, which demonstrates how neural-compressed textures (right) capture sharper detail than previous formats, where the text remains blurry (centre).
