Muhammad Ichsan

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

Thanks for fast response @jh-surh I got error with this way ``` sudo apt-get install cuda-toolkit-11-8 -y git clone https://github.com/jh-surh/gsplat.git cd gsplat git checkout jhsurh/add-pose-grad pip install -e . ```...

Unfortunatelly, the result is not good. @jh-surh @jb-ye This is `kitchen` dataset from `ns-download-data`. Red line is this implementation, The another one is `Nerfstudio v1.0.1` and dataset is processed by...

Seems bug.. I follow this way from `zipnerf-pytorch`'s website, and it works out of box. ``` pip install nerfstudio==1.0.1 cd zipnerf-pytorch git clone https://github.com/SuLvXiangXin/zipnerf-pytorch.git pip install ./extensions/cuda pip install torch-scatter...

So we must add `--pipeline.model.rasterize-mode 'standard'` after `ns-train splatfacto` to see the new result? then "classic" mode is same as Original splatfacto?

I tested on another dataset, so far only 4 tested (`kitchen`, `truck`, `playroom`, and `desolation`). Where 3 of them (`truck`, `playroom`, and `desolation`) I see a little bit improvement. `Kitchen`...

`truck` dataset: **Left =** Using `--pipeline.model.rasterize-mode 'standard'` PSNR = 26,19 dB **Right =** using `Splatfacto v1.0.1`, so it don't use this rasterization. PSNR = 25,97 dB    

> Currently only nerfstudio viewer is supported to display the results correctly. Most other viewers which were designed for the classic mode must accommodate the same change to show the...

I see.. When I activate SO3xR3, I checked the image eval result, the rendered image is little bit shifting due to camera optimization vs GT. I think it was cuprit...

Could you try this draft of `splatfacto` and gives back feedback for his PR? https://github.com/nerfstudio-project/nerfstudio/pull/3113. This PR seems interesting for creating less gaussians but you will get better detail reconstruction.