Muhammad Ichsan

> Is Colmap 3.9.1 compatible with this PR? So far, I can not build `pixsfm` from source if I use `colmap 3.9.1` So I revert back to `colmap 3.8` **Edit:**...

I got unknown error.. This is playroom dataset which is a sample from Inria GS github repo. ``` !ns-process-data images --data /path/to/playroom/images \ --output-dir /path/to/playroom_pixsfm \ --sfm-tool colmap --refine-pixsfm ```...

@Guangyun-Xu hello, I know the problem, we must build from source `colmap 3.8` and `pixsfm` with `ceres-solver 2.1.0` instead of `ceres-solver 2.2.0`. See this bug report: https://github.com/cvg/pixel-perfect-sfm/issues/112 If you have...

Now, please run ``` conda env export --no-builds > environment-nerfstudio.yml ``` so, in the next time, if (someday) your system breaks and you must reinstall python/conda, you can replicate the...

If we don't declare `colmap --load-3D-points`, it was False by Default ` ns-train nerfacto --data ./Nerfstudio/COLMAP_PLY --output-dir ./Nerfstudio/outputs_v1 --pipeline.model.eval-num-rays-per-chunk 8192 --pipeline.datamanager.train-num-rays-per-batch 1024 --pipeline.datamanager.eval-num-rays-per-batch 1024 `  If I declare it...

> Hm yeah, it seems reasonable to make these two consistent. But this change only impacts non-splatting methods where the points aren't used, right? (like nerfacto) > > For the...

Okay, let close it since you said this: ``` If we always set load_3D_points=True for the nerfstudio parser, there will be many cases where this warning will be hit, even...

Interesting. Let me check the quality for another dataset

Hey, any documentation how to test it? or just git clone your repo which you give PR then it run out of the box?

> Hey, any documentation how to test it? or just git clone your repo which you give PR then it run out of the box?  I see new metric...