Muhammad Ichsan

Results 64 comments of Muhammad Ichsan

AFAIK: `transforms.json` = this file records camera poses, images resolution, camera model. It is requirement for using `ns-train` with nerfstudio-data dataparser. Export camera from web viewer = this file records...

Why you want to convert it? You can not use `transforms.json` for `ns-render` and vice versa since it has different functionality.

It is normal since `colmap` use random initialization for every run. But in my experience, Please use `colmap 3.8` for getting more chance higher colmap matched.

Again, interesting PR. :+1: How about the result quality? Hopefully it increase the quality when using `colmap`. Is it compatible with latest `gsplat==0.1.5` ? or we need git install from...

**Sorry**, Unfortunatelly, it decrease the quality: ### `Playroom` dataset processed by `colmap 3.8`: (Red line = this PR) ![image](https://github.com/nerfstudio-project/nerfstudio/assets/60387342/6dc5b0eb-b8d6-414b-99a4-cc2594db889a) ![image](https://github.com/nerfstudio-project/nerfstudio/assets/60387342/49bec2fa-6481-4c94-adc2-99762be6f768) Camera optimization regularizer acts after 3k iters, then the PSNR...

> > Sorry, Unfortunatelly, it decrease the quality: > > This is expected. Like I commented here [#2885 (comment)](https://github.com/nerfstudio-project/nerfstudio/pull/2885#issuecomment-1936410849), there are two separate cases: > > 1. The current NeRF/3DGS...

Hello, interesting PR to be implemented. Here is my own dataset (already processed with colmap) with some of motion blur. Already processed by `colmap` & `colmap image_undistorter` Feel free for...

If one of potential root cause is the opencv bug, Is it already fixed in this commit? https://github.com/nerfstudio-project/nerfstudio/pull/2726

I constantly get better result with **Second Way**. Now I try another dataset. `Truck` dataset from sample Inria 3DGS which I processed using `colmap 3.8` **Blue line =** First Way...

`Purancak` dataset from my friend drone which I processed using `colmap 3.8` **Blue line =** First Way PSNR = 21,68 **Red line =** Second Way PSNR = 22,47 ![image](https://github.com/nerfstudio-project/nerfstudio/assets/60387342/dcfb5431-1315-4dd9-9c7c-32554345db27)