nerfstudio

nerfstudio copied to clipboard

**Describe the bug** If you create a dataset with vertical and horizontal images, colmap will treat this as two different cameras. This breaks the dataloader. **To Reproduce** Take vertical and...

tancik

Get the viewer server to listen to 0.0.0.0

1

Is there any way to launch the viewer on 0.0.0.0? I have to run it on a machine that I can't ssh to (so I can't port forward), but if...

alexandrumeterez

Unable to load a previous checkpoint (Record3d)

5

Hi, I trained a dataset until the default end. Now I want to reload it for setting the camera but I'm unable to do so. If I use this string...

francescofugazzi

qt.qpa.screen: QXcbConnection: Could not connect to display

4

$ ns-process-data --data room.mov --output-dir data/ ``` Number of frames in video: 1616 [07:47:09] 🎉 Done converting video to images. process_data.py:433 [07:47:21] 🎉 Done downscaling images. process_data.py:451 ────────────────────────────────────────────── 💀 💀...

2feet6inches

Multiple GPU performance worse than single GPU

2

``` ns-train nerfacto --machine.num-gpus 2 --vis viewer ``` The output indicates that training is slower with more GPUs. Using two GPUs, I see about 60% CPU utilization, and three GPUs...

catid

Add depth supervision for better results

2

Great work! Record3d generate aligned depth images. Can you update a depth supervision feature with captured depth images for better results?

endlesswho

Not possible to resume training from a checkpoint when training with `--machine.num-gpus 2`

2

**Describe the bug** It is not possible to resume training from a checkpoint when training with `--machine.num-gpus 2`. **To Reproduce** Steps to reproduce the behavior: 1. Run `ns-train nerfacto ......

paul-gauthier

If the auto-orientation methods in the dataparser fails, the scene make look rotated in the viewer. We should add controls in the UI to manually correct for these offsets.

tancik

OSError: CUDA_HOME environment variable is not set. Please set it to your CUDA install root.

3

``` $ pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 -f https://download.pytorch.org/whl/torch_stable.html pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch Looking in links: https://download.pytorch.org/whl/torch_stable.html Collecting torch==1.12.1+cu113 Using cached https://download.pytorch.org/whl/cu113/torch-1.12.1%2Bcu113-cp38-cp38-linux_x86_64.whl (1837.7 MB) Collecting torchvision==0.13.1+cu113 Using cached https://download.pytorch.org/whl/cu113/torchvision-0.13.1%2Bcu113-cp38-cp38-linux_x86_64.whl (23.4 MB) Collecting...

2feet6inches

Runtime Error on Installation

1

**Describe the bug** Runtime Error on Installation Dependency Installation when running this commands pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 -f https://download.pytorch.org/whl/torch_stable.html pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch I have Visual Studio 2022 Installed. error: subprocess-exited-with-error...

jeffreyianwilson