search

digital-standard / ThreeDPoseUnityBarracuda

Unity sample of 3D pose estimation using Barracuda
1.43k stars 275 forks source link

More information about the NN structure? #29

Open OOF-dura opened 3 years ago

OOF-dura commented 3 years ago

ThreeDPoseUnityBarracuda is a sample source which read the onnx by Barracuda and do threeD pose estimation on Unity. the accuracy got better than pre model. *Be aware of that the target should be only one person. It does not work for multi target.

May I know the NN structure you are using and how did you train them? On which dataset? Could you report the performance of the method?

Thank you so much!

allanpichardo commented 3 years ago

It appears to be a version of this network: http://gvv.mpi-inf.mpg.de/projects/VNect/

Here's a tensorflow implementation btw: https://github.com/XinArkh/VNect

marson666 commented 2 years ago

It appears to be a version of this network: http://gvv.mpi-inf.mpg.de/projects/VNect/

Here's a tensorflow implementation btw: https://github.com/XinArkh/VNect

Hi bro, In VNECT paper, the model trained by MPI-INF-3DHP dataset, the keypoints number are not equal to this repo used(24 keypoints number), do you know about the dataset the author used?

Holmex commented 1 year ago

它似乎是这个网络的一个版本：http: //gvv.mpi-inf.mpg.de/projects/VNect/

这是一个张量流实现顺便说一句：https ://github.com/XinArkh/VNect

Hello, may I ask, the C# script used to estimate the pose is named VNect, does it mean that the model used in this article is VNect? Why import a Resnet3_4.onnx model? Is it related to VNect?