Adrian Azzarelli

I modified the 360 script, [check this](https://github.com/albertpumarola/D-NeRF/issues/3#issuecomment-1670073290).

I modified the 360 script to extract data as a singular transforms.json file + render accompanying images ([script](https://github.com/azzarelli/datacollection/blob/main/dnerf_blender_views.py)). Can be easily modified to be reformatted as D-NeRF...

If you look at the transform json files it will help. The tansform json files list time values from 0.0 to 1.0, where the first and last values are 0.0...

Hi, I've encountered the same problem. Were you able to solve it?

For anyone interested in a `dearpygui` viewer for this project (seems a lot more GS papers are using this), I implemented a simple one [here](https://github.com/azzarelli/datacollection/blob/d890ef4aab09f6e03e80944b2e61626646202e72/4DGaussianSplatting/gui.py). You just need to place...

There's other 4D GS models that use deformation and it's not a great solution (honestly this 4D-GS seems like a better approach then most), plus introduces new issues that hex...

I've been stuck on (and still am) avoiding overtraining scenes with sparse views. Through this there's a couple things I think I understand better -> Namely that the regularisers, except...