https://github.com/joonb14/blazeposewithunity

Realtime pose landmark detection with BlazePoseBarracuda in Unity
https://github.com/joonb14/blazeposewithunity

avatar blazepose mediapipe pose-detection pose-estimation pose-tracking realtime realtime-pose unity

Last synced: 4 months ago
JSON representation

Realtime pose landmark detection with BlazePoseBarracuda in Unity

• Host: GitHub
• URL: https://github.com/joonb14/blazeposewithunity
• Owner: joonb14
• Created: 2022-06-08T01:04:12.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2024-05-17T03:42:05.000Z (over 1 year ago)
• Last Synced: 2025-03-17T22:55:16.913Z (10 months ago)
• Topics: avatar, blazepose, mediapipe, pose-detection, pose-estimation, pose-tracking, realtime, realtime-pose, unity
• Homepage:
• Size: 9.41 MB
• Stars: 9
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# BlazePoseWithUnity

Basically using Google's Mediapipe blazepose model which is converted by [creativIKEP](https://github.com/creativeIKEP/BlazePoseBarracuda) 


Thanks to [BlazePoseBarracuda](https://github.com/creativeIKEP/BlazePoseBarracuda) we could extract pose features in real time even at smartphones (S20, S21). 


Then we needed to use these features to move our avatar asset. 


We used method used in [ThreeDPoseUnityBarracuda](https://github.com/digital-standard/ThreeDPoseUnityBarracuda) where model updates skeleton directly by calculating difference between previous and current frame's pose landmarks. (Take a close look at the [VNectModel](https://github.com/digital-standard/ThreeDPoseUnityBarracuda/blob/master/Assets/Scripts/VNectModel.cs))


We modified our code to utillize BlazePoseBarracuda model with VNectModel in ThreeDPoseBarracuda.


### Demo

![pose](./blazepost-sample.gif)