-
-
Hi there! I'm having trouble using tiny-cuda-nn's hash encoding when computing a Hessian matrix. As mentioned in other open & closed issues, [second derivatives are not supported by tiny-cuda-nn's neu…
-
Great work, I was super intruiged by the paper and wanted to reproduce the method for a university project.
Unfortunately I cannot get it to run following the steps from the README, no matter if I …
-
The paths in eval_scene in train_eval_replica_semantics.py are still fixed, while in train_scene they make use of the modifiable CONDA_DIR and PREFIX variables.
Just an issue and not a PR since Its…
-
My input information:
```
dtype:torch.float32
shape:[65535,3]
```
I am sure that my input has no nan.
My encoding config:
```
"encoding": {
"otype": "HashGrid",
"n_levels": 16,
"n_fe…
-
Hi guys,
Thanks for sharing your work. I've tried to run the code on a headless server session with multiple gpus but for some reason I am getting an out of memory error:
```
python scripts/run.p…
-
Hello, when I ran the train file, the following problems occurred, how can I solve it?
D:\Anaconda\envs\naf\python.exe E:/TIGRE/Python/naf_cbct/train.py
['E:\\TIGRE\\Python\\naf_cbct\\src\\encoder\\…
-
Thanks for the excellent work!
I'm trying to reproduce and test some methods in the paper based on nerfstuidio before the code release. I wonder if you can share your ModelConfig of nerfstudio? I ca…
-
following the example process when running `python configure.py build` this is the following output
```
❯ python configure.py build
Consolidate compiler generated dependencies of target phx
[ 1%]…
-
Hi, thanks for open-sourcing such great work!
I noticed the NeRF backbone is based on vanilla NeRF and I'm wondering if it can be replaced by InstantNGP easily to obtain a much faster converge spee…