Issue link: https://digital.copcomm.com/i/1513434
o c t o b e r • n o v e m b e r • d e c e m b e r 2 0 2 3 c g w 1 1 Shutterstock: Generative AI 3D Scene Background Tool Vicon: Markerless Motion Capture System Vicon: Markerless Motion Capture System collaboration with Shutterstock during his SIGGRAPH 2023 keynote address. Shutterstock's generative AI scene background tool is now integrated into Nvidia Picasso, a cloud-based foundry for the devel- opment of generative AI models. The tool allows creators to quickly create and customize 3D scene backgrounds, empowering the next generation of digital content-creation tools and accelerating the model generation workow. Trained on TurboSquid models, Shutterstock's cutting-edge tool allows artists to enhance and light 3D scenes based on simple text or reference image prompts. This generates AI models built with fully licensed, rights-reserved data. Using these prompts, the new feature quickly generates custom 360-degree, 8K-resolution, high-dynam- ic-range imaging (HDRi) environment maps. Artists can then cus- tomize the maps, iterate on ideas, set backgrounds, and light scenes. Artists have previously needed to either purchase expensive 360-degree cameras to create backgrounds and environment maps from scratch or select xed options that may not precisely match their 3D scenes. Now they can simply provide a text or image prompt into Picasso, and Shutterstock's generative AI tools will generate customized panoramic images to achieve their desired visions. "We're committed to hyper-enabling 3D artists and collabora- tors—helping them build the immersive environments they envi- sion faster than ever before and streamlining their content-creation workows using Nvidia Picasso," stated Dade Orgeron, vice presi- dent of 3D innovation at Shutterstock. V I C O N : M A R K E R L E S S M O T I O N C A P T U R E S Y S T E M At SIGGRAPH 2023, Vicon was showing o their new markerless motion capture system in an experience by Dreamscape called "The Clockwork Forest." They had a six-person virtual experience set up on a relatively small volume. As you looked around the space, you just saw a square room with rails on the sides and some peripherals, and an area in the middle with a circular handrail with an opening. You then put on a VR headset and headphones, and the experience began. This was a very dierent VR experience for me. When I looked down, I saw my avatar—which reacted with my movements—and when I would reach out to grab a rail I saw in the environment, I would make contact with a real rail. The hands didn't close because we weren't wearing VR gloves, but as you looked around, you saw the other participants. Although they didn't look the same, you could tell who was who based on height dierence. If you and someone else both grabbed the rail in the same place, you would actually feel your hands touch. During the experience, they cleverly made you feel like you were in a much larger area, walking around and traveling much farther dis- tances than were possible in the actual small volume of the stage. They even gured out ways of separating us within the virtual envi- ronment, and then bringing us back together in a convincing fashion. It was a cool experience, and a great case study for Vicon's mark- erless motion capture system tracking six people simultaneously. — Heath Firestone