search

eververas / 3DGazeNet

Official repo of the paper 3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views
https://arxiv.org/abs/2212.02997
46 stars 4 forks source link

some files are missing #4

Closed ISCo9248 closed 4 months ago

ISCo9248 commented 5 months ago

Hi Vagver, thank you for your open source project I was missing some key files while running the code. The detailed documents are as follows:

xgaze/lms68_3D_all.pkl and xgaze/lms8_all.pkl as mentioned in xgaze_preprocess.py. mpiiface/lms68_3D_all.pkl and mpiiface/lms8_all.pkl as mentioned in mpiiface_preprocess.py. Gaze360/lms68_3D_wbb.pkl, lms68_3D_wobb.pkl, lms8_all.pkl, paths_train_hp90.txt and paths_test_hp90.txt are available in gaze360_preprocess.py.

Are these key files generated by script or in another specific way? Thank you very much

eververas commented 5 months ago

Hello @ISCo9248 ,

Thank you for your interest in our work. We will provide download links for the files you mention soon.

For the time being you could employ the scripts that we already provide to generate the files. The “lms68_3D_all.pkl” files can be extracted using the “tools/preprocess_inference.py script” or your own 3D face landmarks localization algorithm. The “lms8_all.pkl” files can be generated by running the “inference.py” script on your images, using the provided checkpoint.