Processing 24 8K cameras choked CPUs. A direct-to-GPU pipeline eliminated specialized hardware, enabling real-time 3D sports capture.
A sports media innovator aiming to transform live sports into immersive spatial experiences using photorealistic 3D capture technologies.
Delivering broadcast-quality volumetric video required moving over a terabit of data from two dozen 8K cameras in real time, which traditional...
“Spatial media is the next major media format and it requires a carefully orchestrated stack of technologies and workflows to succeed. Delivering real-time, broadcast-quality volumetric video involves moving over a terabit of data from more than two dozen 8K cameras at 120 frames per second via SMPTE 2110 directly into GPUs with GPU Direct, transferring 3D data over InfiniBand to GPU clusters for large-scale raytraced reconstruction, and finally leveraging compression standards to bring immersive sports experiences to fans worldwide. None of this is achievable without the advanced hardware, networking, engineering, AI, and vision that NVIDIA provides.”
Skyrim.AI's 3D video production is part of this use case:
Spatial media platform for immersive 3D sports broadcasting and performance analysis.
NVIDIA is a technology company that specializes in semiconductors, graphics processing units, and artificial intelligence for applications in data centers, gaming, and more.
Related implementations across industries and use cases
RF congestion and cloud lag choked live feeds. Edge AI now identifies jockeys and prioritizes bandwidth for active shots instantly.
Precompiling hardware-specific AI models took weeks per update. On-device generation enabled lightweight, single-package deployments.
Camera-shy executives and scheduling conflicts bottlenecked output. Avatars now generate video on demand without physical shoots.
RF congestion and cloud lag choked live feeds. Edge AI now identifies jockeys and prioritizes bandwidth for active shots instantly.
Processing test batches dragged for 30 hours. Vertex AI now runs the pipeline 23x faster, querying billions of nature images in seconds.
Security fears fragmented AI usage. Now, clear guardrails and automated Slack nudges empower teams to accelerate design and code reviews.
Manually illustrating vintage assets would have tripled production time. Now, a 3-person team uses AI to generate and animate the visuals.
Repetitive coding slowed R&D. Now 80% of engineers use agentic tools to automate work, saving up to 2 hours weekly per person.
Manual testing consumed 20% of developer time. Now, 1,500 engineers use AI agents to auto-generate tests and prototype solutions.
Processing 24 8K cameras choked CPUs. A direct-to-GPU pipeline eliminated specialized hardware, enabling real-time 3D sports capture.
A sports media innovator aiming to transform live sports into immersive spatial experiences using photorealistic 3D capture technologies.
Delivering broadcast-quality volumetric video required moving over a terabit of data from two dozen 8K cameras in real time, which traditional...
“Spatial media is the next major media format and it requires a carefully orchestrated stack of technologies and workflows to succeed. Delivering real-time, broadcast-quality volumetric video involves moving over a terabit of data from more than two dozen 8K cameras at 120 frames per second via SMPTE 2110 directly into GPUs with GPU Direct, transferring 3D data over InfiniBand to GPU clusters for large-scale raytraced reconstruction, and finally leveraging compression standards to bring immersive sports experiences to fans worldwide. None of this is achievable without the advanced hardware, networking, engineering, AI, and vision that NVIDIA provides.”
Skyrim.AI's 3D video production is part of this use case:
Spatial media platform for immersive 3D sports broadcasting and performance analysis.
NVIDIA is a technology company that specializes in semiconductors, graphics processing units, and artificial intelligence for applications in data centers, gaming, and more.
Related implementations across industries and use cases
RF congestion and cloud lag choked live feeds. Edge AI now identifies jockeys and prioritizes bandwidth for active shots instantly.
Precompiling hardware-specific AI models took weeks per update. On-device generation enabled lightweight, single-package deployments.
Camera-shy executives and scheduling conflicts bottlenecked output. Avatars now generate video on demand without physical shoots.
RF congestion and cloud lag choked live feeds. Edge AI now identifies jockeys and prioritizes bandwidth for active shots instantly.
Processing test batches dragged for 30 hours. Vertex AI now runs the pipeline 23x faster, querying billions of nature images in seconds.
Security fears fragmented AI usage. Now, clear guardrails and automated Slack nudges empower teams to accelerate design and code reviews.
Manually illustrating vintage assets would have tripled production time. Now, a 3-person team uses AI to generate and animate the visuals.
Repetitive coding slowed R&D. Now 80% of engineers use agentic tools to automate work, saving up to 2 hours weekly per person.
Manual testing consumed 20% of developer time. Now, 1,500 engineers use AI agents to auto-generate tests and prototype solutions.