ILM uses Omniverse DeepSearch to create the perfect sky

0

For cutting-edge visual effects and virtual production, creative teams and studios benefit from sets and digital environments that can be updated in real time.

A crucial element in any virtual production environment is a sky dome, often used to provide realistic lighting for virtual environments and in-camera visual effects. Legendary studio Industrial Light & Magic (ILM) is harnessing the power of AI to take its skies to new heights with NVIDIA AI-enabled DeepSearch and Omniverse Enterprise.

Capturing photorealistic detail of a sky can be tricky. At SIGGRAPH today, ILM showed how its team, with the NVIDIA DeepSearch tool, used natural language to quickly search through a massive resource library and create a captivating celestial dome.

The video shows how Omniverse Enterprise can give filmmakers the ultimate flexibility to develop the ideal look and lighting to drive their stories forward. This helps artists save time, improve productivity, and accelerate creativity for virtual production.

After refining their search results, the ILM team auditions the remaining sky domes in virtual reality to assess if the asset will perfectly match the shot. By using virtual reality, ILM can approximate what the sky will look like on a virtual production set.

The sky is the limit with AI

A large library with thousands of 3D references and assets provides benefits, but also presents some challenges without an efficient way to search through all the data.

Typically, users set up folders or tag items with keywords, which can take a lot of time. This is especially true for a studio like ILM, which has over 40 years of material in its reference library, including photographs, matte paints, backdrops, and other materials that have been captured over the decades. .

With hundreds of thousands of untagged content items, it is impractical for the ILM team to go through them manually on a production schedule.

Omniverse DeepSearch, however, allows ILM to intuitively search untagged resources using text or a 2D image. DeepSearch uses AI to automatically categorize and search images, which translates to huge time savings for the creative team, eliminating the need to manually tag each asset.

All images courtesy of Industrial Light & Magic.

“With Omniverse DeepSearch, we have the ability to search through real-time data, which is essential for production,” said Landis Fields, lead real-time creator at ILM. “And the ability to search through natural language assets makes it easy for our creative teams to find what they’re looking for, helping them achieve the final look of a scene much more efficiently than before.”

DeepSearch also works on USD files, so the ILM team can review search results and import images into the Omniverse Enterprise 3D space. The artists were then able to interact with the 3D environment using a VR headset.

Together with NVIDIA DeepSearch and Omniverse Enterprise, ILM has the potential to accelerate creative pipelines, reduce costs, and improve production workflows to create compelling content for virtual productions.

Join NVIDIA at SIGGRAPH for more on the latest Omniverse announcements, watch the special business address on demand and attend the world premiere of NVIDIA’s documentary, The Art of Collaboration: NVIDIA, Omniverse, and GTCWednesday, August 10 at 10 a.m. PT.

Share.

About Author

Comments are closed.