On-device pose estimation SDK for fitness and rehab apps
Faster frame generation with higher image quality than NVIDIA DLSS Frame Generation
Stage
Not given
MVP
Founded
2023
Not given
Based in
FR
Not given
Pricing model
Freemium
Open source
Pricing
Free tier: €0, up to 200 tracking API calls monthly, 100 AI credits/month, non-commercial use only. Developer: €50/month, up to 1000 tracking API calls monthly, 500 AI credits/month, commercial use. Business Plan: from €150/month with custom API call limits, custom AI credits, and dedicated support.
Not given
Key features
Free on-device keypoints with 17 COCO points requiring no API key
Rep counting for exercises like squats and push-ups
Joint angle calculations
Form score feedback
Cross-platform: React Native, iOS, Android and web
On-device processing with no video upload
Works offline
WebView and iframe integration option
Ready-to-use built-in motion tracking tools
AI assistant for snippet generation
1.01ms per frame generation on NVIDIA RTX 5090 at 4K 2X
214MB GPU memory at 4K
Super resolution support
Ray reconstruction capabilities
Native Metal support on Apple silicon
What makes it different
Gives fitness and rehab apps vision to analyze actual movement instead of assuming users followed along
Free keypoints tier allows testing and experimentation before paying for analysis features
Single integration works across React Native, iOS, Android and web platforms
Fast real-time performance: 51 FPS on iPhone 12 and 34 FPS on Pixel 5
Higher image quality than NVIDIA DLSS Frame Generation
Uses 62% less GPU memory than DLSS Frame Generation