bmild

For a little bit of context @kwea123 , that part of the code just creates a world coordinate system for the scene such that the object is at the center...

The extract_mesh notebook is not specific to a synthetic object -- if you train a real scene that has 360 degrees of views all around an object and do NOT...

That's right. For forward facing you would get a horrible mesh full of cracks anyway since so much of the occluded content is not observed -- you'd be much better...

The frequency of video saving is controlled by the `--i_video` parameter [here](https://github.com/bmild/nerf/blob/master/run_nerf.py#L822), which has default value 50000. See [`extract_mesh.ipynb`](https://github.com/bmild/nerf/blob/master/extract_mesh.ipynb) for an example of generating a mesh. There's a commented out...

I think that in scenes such as parkstatue, the noise level is so high that some artifacts are hard to avoid, either as a result of COLMAP error or from...

There are a couple ways to go about this. The two easiest are: 1. Construct a new smooth set of `N` camera pose matrices yourself and save it as a...

Did you successfully run COLMAP? There should be a subdirectory `my_dataset_dir/sparse/0/` if so, which should prevent the code from reaching this error.