maturk

> @kerrj Did you test it?  I've run nerfacto-huge and attached visualization at the late stages of training when the gradient BARF is no longer working Yes, as with...

Hi @Jordan-Pierce, it has not been added as a method, however I know someone on the discord channel has been trying to implement the method using nerfstudio and has gotten...

@yifanlu0227 can you try `colmap --auto-scale-poses False` instead of just `--auto-scale-poses False`

yea a similar implementation is the semantic_nerfw model [here](https://github.com/nerfstudio-project/nerfstudio/blob/main/nerfstudio/models/semantic_nerfw.py). I am not so familiar with it, and its not documented but it has the uncertainty loss and other features from...

Problem is external to Nerfstudio in this example. The issue is that the latest versions of Nerfstudio have updated their calls to certain classes, like datamanagers, however, the maintainers of...

what is the issue exactly?

@kerrj, does it make sense to put intermediates in the output dict, since then the viser viewer will try to visualize them as well? Actually, I am thinking that all...

@MohamedAliRashad it is usually pretty hard reimplementing papers, see how long gsplat took xD

There is a branch in nerfstudio that has tried to implement the full zip-nerf algorithm [here](https://github.com/nerfstudio-project/nerfstudio/pull/2242). This was before the code release a few months ago. I am not sure...

For the nerf models, like nerfacto, just make sure you add masks when training. [Here](https://docs.nerf.studio/quickstart/data_conventions.html#masks) you can read more about the mask conventions in nerfstudio. For gsplatfacto/gaussian-splatting the masks are...