yeeu / inverserendernet Goto Github PK

thank you for sharing code!
one stupid question is that in your paper, it seems like we don't need cam parameters to run this model? but in "train.py" and "loss_layer.py", it seems like its needed?

I see it is not possible to download the model from the provided link

It is possible to know the reason why?

Thanks for this interesting work!

Hi, thank you for sharing the code!
In the example of pickle file, I found two arguments "ScaleX" and "ScaleY". However, I cannot find any descriptions of these two arguments. Can you share some details about what are these two args? Thanks in advance!

Hello, thanks for your excellent work!
But I have one question.
In model/pred_illuDecomp_layer.py, there is a function pinv(A, reltol=1e-6). I found that if I reserve this line:
s = tf.boolean_mask(s, s>atol)
the shape of s may become (2,) and then the shape of s_inv becomes (2, 2), which will raise error when do
tf.matmul(s_inv, tf.transpose(u))

So I want to know why need to clear entries lower than reltols_max ?
Does it matter if I don't clear entries lower than reltols_max ?

Thank you!

On the line "from model import SfMNet, lambSH_layer, pred_illuDecomp_layer" I am getting an import error "ImportError: cannot import name 'SfMNet'". I can see SFMnet.py, lambSH_layer.py, and pred_illuDecomp_layer.py in the main directory. I removed "from model" from the line and it seems to work.
Also, it would be good to note somewhere that the mask should be a single-channel image, not RGB.

Hi, this is really helpful and thank you for your contribution to open source!

Could you please share the coordinate system for Spherical Harmonics (SH) and the normal map in your work? Thanks a lot.