Holmes-Alan

cannot use EMD_loss

1

I tried to use "get_emd_loss" for training but it seems there is a problem with backpropagation. loss.backward() File "/home/miniconda3/envs/torch_3d/lib/python3.6/site-packages/torch/tensor.py", line 195, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "/home/miniconda3/envs/torch_3d/lib/python3.6/site-packages/torch/autograd/__init__.py", line...

support for LLFF data format or customized data?

2

Can you please let me know if it supports LLFF data for customized images?

how to play video in a popup window

1

I have a main window and I want to add a function that I can click one button and pop up another window to play a video. Any one can...

using my own data, I can use test.py to generate 360 scene images, but I cannot extract mesh file

1

**Describe the bug** using my own data, I can use "test.py" to generate 360 scene images, but I cannot extract the mesh file. I got something like I think that...

I tried a simple code of using EGNN for feature extraction, it works fine. But when I put it together in network training using pytorch lightning, I got the problem...

pre-trained model for testing

1

Hello, nice work. Would you provide pre-trained models for PCC testing?

code error

1

 There is no definition of "dim" in "model_pugeo.py". Please help me fix it. Thank you!

I understand that you release the trained NeRF-SH models as well as converted plenoctrees. However, when I used your converted plenoctrees for 3D visualization like using "ship.npz" from your file...

Hello there, I tried your code on "chair" example from blender dataset and used the nerfvis library for visualization. It totally worked. However, when I tried to visualize other examples,...

I tried to use "get_emd_loss.py" but I met this problem RuntimeError: Expected isFloatingType(grads[i].type().scalarType()) to be true, but got false. (Could this error message be improved? If so, please report an...