Pingu
Pingu
> Thanks for your great work! When evaluating 3D face reconstruction , you compared with 3DDFA which is based on BFM. The difference between 3DDFA(50k) and PRNet (40k)is the number...
Hi, Did anyone get the training code from the authors?
> Please use tensorflow>=2.3.0 Thank you for your reply. I wanna use your code in my own network which should be implemented in TF1.13. Is there any other way to...
> > Can I use 68 landmarks instead of 5 landmarks？ > > I think yes. In load_img.py insert your own landmarks loading with correct indices, from 68 you need...
> > This is quite strange. Does the output .obj file seems reasonable? You can also check the value of each pixel in the recon_img to see if there is...
Thanks for your reply. So, it means you do not use **Confidence Net** in your model? or you've used Confidence Net in your model but haven't released it's code?!
Gotcha! Thanks for your clarification!
> @zomkey > Hi, I am very interested in this work too, if convenient, could you send me your training codes so that I can learn the process better? >...
> Hi! > > So, I need to produce the texture files separately in the form of a texture_map and uv_position_map as is being done in https://github.com/YadiraF/face3d/blob/master/examples/7_generate_uv_map.py. > > So,...
> I want a get the 2d face(texture) image like PRNet UV map, but the texture of the model's output is a vector, so Can I change it to a...