-
Hi,
when I run the data preparation demo with the soldier and octree depth of 7 the mesh that is reconstructed for debugging purposes has strange slits/holes (see screenshot) - is this normal?
!…
-
Congrats on this great work, and thanks a lot for open-sourcing this project!
1. I wonder why we need to retrain the blend weight fields of unseen human poses? It seems can directly use the Nerf an…
tpzou updated
2 years ago
-
### Description
We are unable to produce macosx wheels on x86_64 with a tag any other than 12_0.
We set `MACOSX_DEPLOYMENT_TARGET=10.13`. See [the resulting build log](https://github.com/scikit-i…
-
Hi Chen-Hsuan,
I successfully created an experiment in the iphone.py style. That is, without any information of camera poses. Is it possible to create a 3D model from the output?
Thanks in adva…
-
-
This proposal is a summary and formalization of various past discussions about double support, especially [issue #288](https://github.com/godotengine/godot/issues/288) which this proposal directly sup…
-
I am wondering whether it's possible to revert the rotation applied by the marching cubes algorithm after obtaining the watertight meshes. The scaling and translation components can easily be retrieve…
-
Hi
Thank you again for this research work.
So I could train perfectly using default parameters.
Now when I run test to create mesh, I am getting this error:
```
Traceback (most recent call last):…
-
I'm having trouble with running the --save_mesh feature in /scripts/run.py.
When I run the following command, I get these errors about illegal memory access. Is this due to GPU ram being too small?…
-
Thanks for the great work and releasing the code.
Here I am testing the inference(rendering) quality of Nice-SLAM, i.e. loading pretrained decoders and feature grids from the provided checkpoints a…