lansburych / relightable-nr Goto Github PK

I get the above error on running bash train_rnr.sh.
Its not error with script but the torch-scatter is not getting imported
I installed it via
pip --no-cache-dir install torch-scatter==1.3.2 -f https://pytorch-geometric.com/whl/torch-1.1.0.html
as given in readme of your code.
Can you help/assist with this error?

Hi Lansbury
Thanks for sharing the impressive work!
I have running into the following error, any insight on this problem?

Traceback (most recent call last):
File "train_rnr.py", line 304, in
lp_stitch_resize = torch.from_numpy(lp_stitch_resize).to(device)
RuntimeError: CUDA error: invalid device ordinal

Does the code requires more than one GPU?

Best,
tuotuo

Hi! Thank you for the astonishing work! Could you please clarify, is it possible to use for the second lightning conditions (rgb1) photos taken under the different camera poses (and even maybe the different number of the photos)

Hello,

Thanks for the code and your work!
Could you please upload the stitched environment for the 'Dyck' scene?

Thanks!

Hi @LansburyCH awesome work
Could you please share your DNR implementation? We needed to compare it with our current research. TIA

Sorry to bother you, I changed my own data for the test of the relightable-nr model. My data is face mesh, and I have replaced the tex with the diffuse map of the face, but in the training results, the effect of relighting is not very good, the face looks like a metal-like material. After checking the source code, I found The loss of relighting results and relighting ground truth is not added to the loss function, so I wonder if this is the cause of this problem?

Hi，thank you for the code!
I used my own data to run the precompyte.py, but got empty uv maps and the other maps. What the problem might be? By the way , is the global_RT essential for the data and how to set it correctly?

Thanks！

Hi@LansburyCH, I want to reproduce the paper with my own model data, but I don't know how to make calib.mat， Could you please tell me the meaning of each parameter in this calib.mat?

Hi,
Thanks a lot for your great work!
I am curious about the meaning of relightable and its relationship with free viewpoint video?