darlinghang / st-nerf Goto Github PK

Will you release the training code?

Hello,

I am trying to download the dataset from the Baidu drive, but it asks me to use the Netdisk client which tells me to log in with a Baidu account. It seems impossible for me to create a Baidu account with a belgian (+32) phone number.

Is it possible to upload the dataset to some other public drive (google, etc)? Or maybe do you have an idea for how I could download it from that drive when being outside of China?

Thanks in advance.

I wanted to know whether you didn't implement the rotation and the duplication of the datasets, because I didn't get it to work. I tried to set the Rotation in the init-method but it didn't change anything.

I am confused by your synthetic dataset:

1. How do you generated the ground-truth frames for the 36 virtual cameras?
2. Why does the number of virtual cameras changes from 36 to 17 (Tab. 3)?

The link https://drive.google.com/drive/folders/13YHw_YSGewvcgYdwqbelM9L2JiPNWLi7 seems empty, and I can't download the dataset. Could you please update the link and share the dataset? Thanks very much!

Thank you for sharing your dataset.
I wonder what is the coordinate frame for the RT_c2w.txt files.

Hello authors, thanks for your pretrained model. I render the images of walking and ｔａｅｋｗｏｎｄｏ sequences and calculate the PSNR and SSIM metrics.

They are slightly different from your paper. Is that normal?

Hello,

I cannot install the torchsearchsorted package, the following error is returned :

Failed to build torchsearchsorted
Installing collected packages: torchsearchsorted
Running setup.py install for torchsearchsorted ... error

Do you know what the error might be?

@DarlingHang
what is minimum RAM of GPU required for the project as the process is being killed in my system due to RAM exhaustion.??
Please Guide me..

RuntimeError:Tried to access nonexistent attribute or method 'call.' of type "'.torch.-.konia.geometry.boxes.Boxes3D'. Did you forget to initialize an attribute in init()?:
File "E:\Anaconda3\envs\st-nerf\lib\site-packages\kornia\geometry\boxes.py"，line 718# Due to some torch.jit.script bug (at least <= 1.9), you need to pass all arguments to .-init__ when# constructing the class from inside of a method.
return cls(hexahedrons, raise if_not floating point=False mode=mode)222 <--- HERE

Hello, the following errors occur when I run the test code. How can I solve them

Hi, in the latest torchvision version 0.14.0, the parameter for T.functional.rotate change from resample to interpolation and will update to interpolationnum in 0.15.0

Since in this repo, this function used in random_transform.py, I hope you can update this change of param.
I hope this can help people who want to implement this repo in latest environment.

Hi author:

I hope to use your dataset to do some work in NeRF. Could you tell me some details in the dataset? I found that your config file shows both FIX_FAR and FIX_NEAR are -1. Could you tell me why both of them are the same? I would appreciate it if you can help me.

Hi，it seems that VIEW_MASK should be setted as not none! How to solve this problem? @DarlingHang

Hi,

I am trying to download the walking sequence. However, the OneDrive link only contains the taekwondo and the boxing sequence but not the walking one. Could you provide the download link for the walking one?

Many thanks in advance!

Xuan

python demo/taekwondo_demo.py -c configs/config_taekwondo.yml
Traceback (most recent call last):
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\OpenGL\platform\egl.py", line 67, in EGL
return ctypesloader.loadLibrary(
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\OpenGL\platform\ctypesloader.py", line 45, in loadLibrary
return dllType( name, mode )
File "D:\D\anaconda\envs\st-nerf\lib\ctypes_init_.py", line 373, in init
self._handle = _dlopen(self._name, mode)
FileNotFoundError: ("Could not find module 'EGL' (or one of its dependencies). Try using the full path with constructor syntax.", 'EGL', None)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "demo/taekwondo_demo.py", line 23, in
from render import LayeredNeuralRenderer
File ".\render_init_.py", line 4, in
from .neural_renderer import NeuralRenderer
File ".\render\neural_renderer.py", line 9, in
from .bkgd_renderer import PrRender
File ".\render\bkgd_renderer.py", line 7, in
import pyrender as pr
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\pyrender_init_.py", line 3, in
from .light import Light, PointLight, DirectionalLight, SpotLight
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\pyrender\light.py", line 10, in
from OpenGL.GL import *
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\OpenGL\GL_init_.py", line 3, in
from OpenGL import error as _error
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\OpenGL\error.py", line 12, in
from OpenGL import platform, configflags
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\OpenGL\platform_init.py", line 35, in
load()
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\OpenGL\platform_init.py", line 32, in _load
plugin.install(globals())
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\OpenGL\platform\baseplatform.py", line 92, in install
namespace[ name ] = getattr(self,name,None)
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\OpenGL\platform\baseplatform.py", line 14, in get
value = self.fget( obj )
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\OpenGL\platform\egl.py", line 93, in GetCurrentContext
return self.EGL.eglGetCurrentContext
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\OpenGL\platform\baseplatform.py", line 14, in get
value = self.fget( obj )
File "D:\D\anaconda\envs\st-nerf\lib\site-packages\OpenGL\platform\egl.py", line 73, in EGL
raise ImportError("Unable to load EGL library", *err.args)
ImportError: ('Unable to load EGL library', "Could not find module 'EGL' (or one of its dependencies). Try using the full path with constructor syntax.", 'EGL', None)

platform: win10