TimoBolkart

Thank you for your interest in TEMPEH. As TEMPEH is trained on a constrained multi-view face dataset with a fixed set of cameras (i.e., only with a small variation in...

TEMPEH applies a U-Net type feature extractor network to each of the input images to extract feature maps. As the model is trained on a single dataset with similar views...

Unfortunately, I have no experience with running the inference on Windows. The code and model itself were only tested on different Linux distributions. What Pytorch version are you using?

This seems correct. Maybe try re-downloading the model, just to make sure that the downloaded file was not corrupted. Otherwise, I don't have any good idea on why you can't...

Thank you for the answer @why986. Does the download work for you @Garv62003, when pasting the download link to the browser?

Hi, can you please specify what exactly you did? Just zero-ed out the matrix entries for the vertices outside the mask? What is the dimensionality of your adapted correspondence matrix?...

I can forward your request to our technical artist who also created this plugin. If you send your request to [email protected], I can directly put you in cc.

Apologies, can you please re-send it to the other email? It seems the tbolkart one is no longer forwarded after I left MPI.

That is weird, as I still got several emails delivered to the other address. I have meanwhile talked to the technical artist who created the current plugin. It seems that...

The data used for training are unposed, meaning that effects of global translation, global rotation, and the head rotation around the neck are removed. Please refer to Section 6 of...