nerfstudio

nerfstudio copied to clipboard

question regarding ns-process-data

4

Thank you for your project. While attempting to construct a dataset from a video using ns-process-data, I encountered a challenge regarding the match rate of poses and images as reported...

Aru321

Hello, With COLMAP, it is possible to extract data to determine which images and keypoints correspond to specific 3D points and to identify which images have been matched. I am...

abrahamezzeddine

**Description** When training Splatfacto on a VR-NeRF dataset, it crashes after 17910 steps with this error: `File "/root/miniconda3/envs/nerfstudio/lib/python3.8/site-packages/torch/autograd/__init__.py", line 251, in backward Variable._execution_engine.run_backward( # Calls into the C++ engine to...

bernard0047

Question Regarding Image Downscaling Method

3

https://github.com/nerfstudio-project/nerfstudio/blob/9b3cbc79bf239eb3c69e7c288632aab02c4f0bb1/nerfstudio/models/splatfacto.py#L83 Why was the following method chosen for downscaling images instead of directly using [F.resize](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.resize.html)? ```python def resize_image(image: torch.Tensor, d: int): """ Downscale images using the same 'area' method in...

wzy-99

Upgraded resize_image function to support interpolation

1

Replaced convolution operation with interpolation. Added support for downscaling using floats. resolves #3263

JTStephens18

**Describe the bug** When running splatfacto-w it will not run. I cannot work out what is meant by "To train with it, download the train/test tsv file from the bottom...

sion3951

zip nerf is not working 360.gin file is missing

8

as soon we start to train a model after processing an images with comlap. below isssues are coming ``` ERROR:root:Path not found: /configs/360.gin Traceback (most recent call last): File "C:\Users\sum11525\Anaconda3\envs\nerfstudio1\lib\runpy.py",...

sumanttyagi

tiny-cuda-nn- installation fails

1

Might want to add this to the readme. ``` $ pip install ninja git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch ... In file included from /home/dheera/miniconda3/envs/nerfstudio/include/cuda_runtime.h:83, from : /home/dheera/miniconda3/envs/nerfstudio/include/crt/host_config.h:132:2: error: #error -- unsupported GNU version! gcc...

dheera

Attemping to use the websocket viewer throws and error and fails to display: `(viser) Connection opened (434, 418 total), 148 persistent messages connection handler failed Traceback (most recent call last):...

DrAwkward33

**Describe the bug** Im trying to train a model on SLI RTX 2080 ti on a windows 10 machine. `ns-train nerfacto --pipeline.model.predict-normals True --data {PATH} --machine.num-devices 2` I get the...

anishpatel44