Closed elimarinoiu closed 2 weeks ago
Hi elimarinoiu,
I did some experiments with a normal detector with FFHQ images, but decided not to include it in the repo since I wasn't sure about the benefits. FYI you can look at this repo for the normal detector that I used.
I never used normals for tracking in videos. It is hard to tell what causes the complete failure that you are experiencing, but here a few things that you can look at:
--no-intrinsics_provided
?Kind regards, Simon
Hi Simon,
Thanks for your suggestions and clarifications! 1) The metrical tracker is not perfect, but seems ok. 2) No extreme head poses (just having a small part of head out of the image). 3) One single face, landmarks, masks look good. 4) Shadows seem normal to me. 5) Still looks poor on one image. 6) Yes. The images are quite low res (224x224). I added some screenshots of the metrical tracker and stage 1 mesh.ply. I might be missing something obvious but I didn't figure it out yet.
Best regards, Elisabeta
I see, that is defenitely not expected with that image. Can you try again but resize the image to 512x512? That worked for me using a screenshot from your image
Hi,
Thanks for your suggestion. It worked for me, as well!
Best, Elisabeta
Hi,
I tried to run the code on a video sequence of my own and the results look deformed. I noticed that after running the preprocessing code there was no normals directory generated - as I have seen in the provided FFHQ examples for which the 3d reconstructions look very good. I have also noticed that face_normals/pretrained_models/ is empty. This directory is created when installing the associated code in running install_preprocessing_pipelines.sh but I have failed to see where this code is called - I would have expected in preprocessing/run.sh.
My questions are 1) am I missing something regarding the computing of the normals? Do I need to run something else and/or download the associated model? 2) Do you think the missing precomputed normals could cause the deformed results on my data?
Thanks!