real scene test, get poor result about torch-ngp HOT 13 CLOSED

@neilgogogo Hi, In fact I found some related issues:

• NVlabs/instant-ngp#178
• actions/runner-images#3485

You may have a try at these workarounds:

• change /std=c++14 to /std=c++17 in all backend.py
• downgrade VS toolset by setting -T version=14.25 for cmake
• upgrade both VS and CUDA to the latest version

from torch-ngp.

@neilgogogo Hi, have you tried the GUI, so you can visualize which regions are blurred?

from torch-ngp.

hi, thank you for your reply.
I try to run it on windows, but get the following error when compling the cuda

from torch-ngp.

Could you give more details on the enviroment? e.g., CUDA version, VS version, ..
also check this thread.

from torch-ngp.

I tried to downgrade the environment to cuda11.3.
And it comes the following compiling errors.

windows10
Cuda compilation tools, release 11.3, V11.3.109
Python 3.8.5
torch1.11.0+cu113
VS2019
RTX3060

from torch-ngp.

The error is strange... Could you post the full error log, or at least the first error? Also, can you install tiny-cuda-nn?

from torch-ngp.

The error is strange... Could you post the full error log, or at least the first error? Also, can you install tiny-cuda-nn?

sorry, it is really a long error, and the start is limited by the powershell. Perhaps it is still due to the environment issue when compling the hashencoder.

from torch-ngp.

hi, thank you for your advice. When I change C++14 to C++17, it works;)

from torch-ngp.

hi, when I visualize the training, the view is like this. I think the reason might be the camera coordinate? But I am not sure.

Is it possible to visualize the training camera poses and bounding box in dearpygui, so it might be more easier to debug.

from torch-ngp.

It's not implemented now, but telling from the second figure, the camera poses are not properly transformed. They should be centered around the unit sphere, an example:

You could try running colmap2nerf.py on the original images, or if you already have the poses, you could refer to these parts to properly adjust them.

from torch-ngp.

hi, using the tensoRF, I reconstructed the target. But the reconstructed resolution is not good after 1000epochs*64 steps. I find there are resolutions 0 and 1 in the main function. Do you think increasing it will increase the resolution? Or how to increase the image resolution do you think， such as increasing the sigma_rank, color rank.

from torch-ngp.

64 steps sound too few... I thought the default is 512 steps?

from torch-ngp.

thank you for your advice, I will try;)

cheers

from torch-ngp.