Theia3D Now Supports NVIDIA GeForce RTX 50 Series Graphics Cards

April 3, 2025
Theia
BIO
Recent Posts
How Sanford Health Scaled Their Return-to-Play Program with Markerless Motion Capture
Sanford Health, one of the largest U.S. integrated health systems, faced challenges scaling motion capture assessments across clinics due to the limitations of traditional marker-based systems. Managing over 500 ACL evaluations per year, they needed a more efficient, consistent, and scalable solution. By integrating Theia3D markerless motion capture with Qualisys, Sanford streamlined workflows, eliminated the need for technical expertise, and achieved cross-site consistency. The result: faster evaluations, reduced setup time, and reliable data collection that supports high-quality return-to-play decisions across multiple facilities.
Introducing Theia Axiom - Our First Major 2025 Software Update is Here
You’ve seen the new brand. Now meet the software to match. Theia Axiom, our first major update of 2025, is now available. With a refreshed interface and improved usability, Theia Axiom brings visual polish and functional upgrades to both Theia3D and Theia3D Batch. In this post, we’ll cover what’s new.
Early Specialization in Ice Hockey Goaltenders: Considerations for Hip Health & Injury Risk
A recent study published in the Journal of Orthopaedic & Sports Physical Therapy (JOSPT) investigates the relationship between early sports specialization and hip kinematics in ice hockey goaltenders. Using Theia3D markerless motion capture technology, researchers examined how hip movements differ between early specialized (ES) and non-early specialized (NES) goaltenders. The findings suggest that ES goaltenders demonstrate distinct hip movement patterns, potentially as a strategy to mitigate injury risk. This research provides important insights into training practices, injury prevention, and sport specialization guidelines for young athletes.

Summary

Following our first major software update of 2025 - Theia Axiom - Theia3D now supports the newest generation of graphics cards from NVIDIA - the GeForce RTX 50 Series. These new graphics cards deliver significant performance improvements, allowing you to further push the limits of your markerless motion capture workflow with Theia3D. In this post, we break down what this update means for processing speeds and productivity.


Leading Motion Capture Meets NVIDIA’s Powerful GPUs


At Theia, we’re committed to advancing the capabilities of markerless motion capture. Theia3D uses advanced computer vision algorithms to extract high-quality 3D human movement data with unmatched ease of use, flexibility, and research-grade accuracy.

Your time is valuable, but so is reliable, biomechanically accurate data. That’s why we invest heavily in performance testing to ensure Theia3D not only meets the highest research standards, but also keeps pace with hardware innovation. 

With the release of Theia3D Axiom and now support for the NVIDIA GeForce RTX 50 Series, we’re unlocking a new level of processing speed - without compromising accuracy. To map out this new performance landscape, we’ll be benchmarking the new graphics cards against the previous flagship model, the GeForce RTX 4090, over the coming weeks.


Benchmarking: RTX 4090 vs. RTX 5080


Since NVIDIA’s announcement of the 50 Series at the start of 2025, we’ve been eager to test these next-gen GPUs. Given the performance leap we saw with the 40 Series, we anticipated big things - and the early results are impressive.

In our first round of benchmarking, we compared the RTX 5080 against the previous flagship, the RTX 4090, using standard Theia3D settings. Here’s what we tested:
‍
Test Setup‍

  • Graphics cards:
    ‍
    • NVIDIA GeForce RTX 4090 vs. NVIDIA GeForce RTX 5080
  • Theia3D Settings:
    ‍
    • Standard GPU configuration for each card in Theia3D
    • Default Person Detection Threads
    • Default Joint Detection Threads
    • Person Detector Skip Frames: 3
  • Dataset:
    ‍
    • 7 cameras
    • 1750 frames per camera
    • 960 x 540 resolution
    • AVI file type with MJPEG encoding
    • Standard Theia3D configuration for each

Performance Results

The results of the test speak volumes. The RTX 5080 significantly outperformed the 4090 - leading to major reductions in processing time (a reduction of 30%). These results are even more impressive considering that the RTX 5080 is a mid-tier card from the 50 Series - yet it outperformed the previous generation’s flagship model, the RTX 4090. If this is what the 5080 can do, we can’t wait to test the RTX 5090. 

Theia3D Benchmark: RTX 4090 vs. RTX 5080
Metric GeForce RTX 4090 GeForce RTX 5080 % Change
Person Detection Time [s] 37.6 18.2 52% shorter
Rate [fps] 325 673 107% faster
Skip Frames = 1 Rate [fps] 108 224 107% faster
Joint Detection Time [s] 42.1 34.1 19% shorter
Joint Detection Rate [people/s] 657 811 23% faster
Total Processing Time 1 min 30 sec 1 min 4 sec 29% shorter


Throughout our testing, both cards performed reliably under sustained loads. For those monitoring their own GPU performance, we recommend GPU-Z - a simple, effective tool for real-time GPU diagnostics.


Theia Axiom: Ready for the Future


With this update, Theia Axiom now officially supports the NVIDIA GeForce RTX 50 Series, opening up possibilities for even faster, more powerful motion capture processing. Whether you’re analyzing gait, sports performance, or clinical rehab, this upgrade will help you process more data in less time. 

Stay tuned - more benchmarks (including the RTX 5090) are on the way.


Get Started with Theia Axiom


Theia Axiom is available now through our customer support portal.

Want to see it in action? 

‍

Recent Posts
How Sanford Health Scaled Their Return-to-Play Program with Markerless Motion Capture
Sanford Health, one of the largest U.S. integrated health systems, faced challenges scaling motion capture assessments across clinics due to the limitations of traditional marker-based systems. Managing over 500 ACL evaluations per year, they needed a more efficient, consistent, and scalable solution. By integrating Theia3D markerless motion capture with Qualisys, Sanford streamlined workflows, eliminated the need for technical expertise, and achieved cross-site consistency. The result: faster evaluations, reduced setup time, and reliable data collection that supports high-quality return-to-play decisions across multiple facilities.
Introducing Theia Axiom - Our First Major 2025 Software Update is Here
You’ve seen the new brand. Now meet the software to match. Theia Axiom, our first major update of 2025, is now available. With a refreshed interface and improved usability, Theia Axiom brings visual polish and functional upgrades to both Theia3D and Theia3D Batch. In this post, we’ll cover what’s new.
Early Specialization in Ice Hockey Goaltenders: Considerations for Hip Health & Injury Risk
A recent study published in the Journal of Orthopaedic & Sports Physical Therapy (JOSPT) investigates the relationship between early sports specialization and hip kinematics in ice hockey goaltenders. Using Theia3D markerless motion capture technology, researchers examined how hip movements differ between early specialized (ES) and non-early specialized (NES) goaltenders. The findings suggest that ES goaltenders demonstrate distinct hip movement patterns, potentially as a strategy to mitigate injury risk. This research provides important insights into training practices, injury prevention, and sport specialization guidelines for young athletes.
In this blog
Summary