search

AaronJackson / vrn

:man: Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"
http://aaronsplace.co.uk/papers/jackson2017recon/
MIT License
4.52k stars 742 forks source link

Other trained models? #14

Closed mshreve closed 6 years ago

mshreve commented 6 years ago

In the paper, you describe 3 models: VRN, VRN-multitask, and VRN-guided. I believe that the model included in the framework is only the first; do you plan on releasing the other two?

Very much appreciate the code, thanks for releasing!

Matthew

AaronJackson commented 6 years ago

Hi Matthew,

We are not planning to release the additional models, at least not anytime soon, since we'd like to keep something for potential industry collaboration.

Sorry about that!

Thanks,

Aaron.

mshreve writes:

In the paper, you describe 3 models: VRN, VRN-multitask, and VRN-guided. I believe that the model included in the framework is only the first; do you plan on releasing the other two?

Very much appreciate the code, thanks for releasing!

Matthew