PRNet-PyTorch
PRNet-PyTorch copied to clipboard
The training and evaluation code for PRNet (《Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network》)
sorry to bother you and thanks for release your version on github. But i have some questions about NME. when i try to get the NME of PRNET, i got...
Hi @reshow I had a question regarding generating a 3D mesh. For this, we need vertices (N*3), textures(N*3) and triangle indices. But in a case that the output of our...
Hi, @reshow, thanks for you work. I run processor.py to generate UV position maps. And as follow is the result. But it is different from paper in the paper. source...
Thanks for your great work! When evaluating 3D face reconstruction , The ECCV paper compared with 3DDFA which is based on BFM. The difference between 3DDFA(50k) and PRNet (40k)is the...
Hi @reshow , Thanks for this repository. Would you please share the evaluation code? The code which you used for evaluating the results! (NME I mean) Thanks.
Thanks for your work. I send qq e-mail , but i did not accept reply all the time.Can you share your resource and help me? thx.
Hi @reshow In file augmentation.py, there is a **rotateData** function, whose input are x, y, ..... . Obviously, x is the network input image, y is the uv_position_map(or target, label,...
Hi,Would you mind telling me how your model is trained? I didn't use the code to achieve your model effect.
I generate the 3dface Out file, but it has no mean_uv_posmap.npy
hello,thanks for your repo, i wanna know how to estimate pose in this repo,could you share the code or the way of this issue. thx a lot