search

digital-standard / ThreeDPoseUnityBarracuda

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

How can i change the video screen from video player to the picture that we input to the model? #19

Open karta1310041 opened 3 years ago

karta1310041 commented 3 years ago

Hello, I try to apply this project to virtual try-on, but I found that the background(video screen)'s texture is not the picture we input to the vinect model. It led the try-on effect have some delay, so how can I change the code for after vnect caculated the 3d keypoint and update the texture we input to the video screen. Thanks!!!!

alezuky commented 3 years ago

Hello. I found that the picture that is used at VNect model is at the Main Texture object. You can see it at the Update() function from the Barracuda Runner Script. Hope this information helps you.

karta1310041 commented 3 years ago

Hello. I found that the picture that is used at VNect model is at the Main Texture object. You can see it at the Update() function from the Barracuda Runner Script. Hope this information helps you.

Thanks for your reply. But the Main Texture's picture is after cropping 448*448, but I need the orignal size. Thanks.

yukihiko commented 3 years ago

I think the targetTexture of the camera was MainTexture and its size was 448. Why not make the MainTexture the desired size and trim the texture for the training model?