ashawkey / torch-ngp

A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

ashawkey/torch-ngp Issues

Depth Output 0 or Nan
Updated 2 months ago
What is tiledgrid?
Updated 2 months ago
LNK1181
Updated 3 months ago2
ModuleNotFoundError: No module named '_raymarching'
Updated 3 months ago8
The growth process of `local_step` seems to have an issue.
Updated 4 months ago
This is strange, I haven't met this problem. Could you try to install some other packages that require building extensions? For example, `pip install torch-scatter` following [this](https://github.com/rusty1s/pytorch_scatter#from-source)?
Updated 4 months ago
build extension problem
Updated 4 months ago1
A tip to use smpl camera data to use with torch-ngp? Which transformation do we use?
Updated 5 months ago
_raymarching_face/_raymarching_face.so: cannot open shared object file
Updated 6 months ago3
D-NeRF does not perform well when running the HyperNeRF data set. Does it need to make some adjustments?
Updated 6 months ago
CUDA 12
Updated 6 months ago
"Ninja is required to load c++ extensions" && "fail to build pysdf"
Updated 7 months ago1
issues when build extensions:ERROR: Could not build wheels for raymarching, which is required to install pyproject.toml-based projects
Closed 7 months ago1
issues when build extensions
Closed a year ago5
About GUI
Updated 8 months ago
About environments！
Closed 8 months ago1
ImportError: No module named '_hash_encoder'
Updated 8 months ago
OK. Thank you for your response!
Updated 8 months ago
fail to rebuild radiance field. such as fox, lego
Updated 8 months ago1
about llff dataset
Updated 8 months ago3
D-NeRF
Updated 8 months ago1
RuntimeError: Error compiling objects for extension while building extension
Updated 9 months ago6
Ambient Occlusion (AO) using the (Instant-NGP framework)
Updated 9 months ago
Hi. I had a question about the dataloading step. Why does all the data need to be loaded in a single step. I am running out of GPU memory. Is it possible to do it in batches.
Updated 9 months ago
Control Time in GUI for D-NeRF
Closed 10 months ago1
Interpolation in GridEncoder might be wrong?
Closed 10 months ago1
The value of `self.cascade` becomes 0 when `bound <= 0.5`, causing errors
Updated 10 months ago
hi, I have some questions when using 'test' mode after trained a model with custom data
Updated 10 months ago
custom autograd backward
Updated a year ago1
GridEncoder can't handle empty positions
Updated a year ago
Is D-NeRF the version in the original paper?
Updated a year ago
Please how to solve this problem？
Updated a year ago5
Sometimes, start from white result
Updated a year ago1
No CUDA runtime is found, using CUDA_HOME='C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.1'
Closed a year ago
SDF Performance
Updated a year ago
num_rays(N) is 2073600, num_sigmas is 2073728?
Updated a year ago
Question on nerf matrix to ngp
Updated a year ago
need some camera-parameter-free (need not colmap) NeRFs algorithms implementations.
Updated a year ago
There is no SDF/gui
Updated a year ago
why can't i load the data?
Closed a year ago1
The GUI does not display on
Closed a year ago2
Low GPU usage
Updated a year ago
D-NeRF CUDA out of memory
Updated a year ago
Supporting bfloat16
Updated a year ago
Using temporal basis to model dynamic scene
Updated a year ago
CUDA Error while using X11 to display GUI
Closed a year ago1
Possible bug and difference between scale and resolution?
Closed a year ago1
Encoding parameters
Updated a year ago
A question about the network
Closed a year ago1
[BUG?] GridEncoder doesn't give correct gradient with respect to the coordinate
Closed a year ago2