maum-ai/hififace

How to use Deep3dFaceRecon model?

Feywell opened this issue · 1 comments

Thanks for you great work to reimplement hififace!
I find that you use the Deep3dFaceRecon model straightly in size (256, 256). But the offical code of Deep3dFaceRecon is (224, 224).
Did you train the model use size (256, 256)?

From my experience, using 256x256 should be fine. Also, the Deep3dFaceRecon repo mentioned that they applied a number of augmentations during training. So I thought Deep3dFaceRecon should be robust enough to different image sizes.