AI Pose Estimation Engine
featuring real-time 2D/3D human skeleton detection with 30 keypoints

About VisionPose

VisionPose is a high-precision AI pose estimation engine which detects multi-person skeletons from camera images without the use of markers or depth sensors.

  • Detecting 30 keypoints of the human body at max 60 FPS in real time
  • 3D inference with 2 cameras (Standard),
    3D inference with a single camera (Single3D*)
  • No usage restrictions, including commercial use

Application Fields

  • Sports Biomechanics
  • Medical Care and Rehabilitation
  • Manufacturing
  • Crime Prevention and Security

Product Lineup

VisionPose Standard

Standard VisionPose with Accuracy & Performance
3D Inference Using Dual Cameras

VisionPose Single3D

Easy Pose Estimation for Windows Unity or iOS/iPadOS
3D Inference Using a Single Camera

for iOS/iPadOSComming soon

3D Inference

30 Keypoints
Dual Cameras

17 Keypoints
Single Camera

2D Inference

30 Keypoints
Single Camera

Platform

Windows C#
Windows C++

Linux (Ubuntu)

Jetson AGX Xavier
Jetson Xavier NX

Unity

iOS / iPadOS

VisionPose Standard

Standard VisionPose with accuracy & perfomance
3D inference using dual cameras

3D Inference

30 Keypoints
Dual Cameras

2D Inference

30 Keypoints
Single Camera

Platform

Windows C#
Windows C++

Linux (Ubuntu)

Jetson AGX Xavier
Jetson Xavier NX

VisionPose Single3D

Easy pose estimation for Unity or iOS/iPadOS
3D inference using a single camera

for iOS/iPadOSComming soon

3D Inference

17 Keypoints
Single Camera

2D Inference

30 Keypoints
Single Camera

Platform

Unity

iOS / iPadOS

Examples

Used by more than 300 clients

News / Topics