maturk

@louhz I still need to work on it yea, just haven't had the time recently.

Hey @rosejn, here is a quick hack that lets you render depths: ```python depth_out = RasterizeGaussians.apply( self.xys, self.depths, self.radii, self.conics, self.num_tiles_hit, self.depths[:, None].repeat(1, 3), torch.sigmoid(self.opacities), self.H, self.W, )[..., 0:1] ```

@cat-state, any ideas how to do the expected ray termination with these gaussians? In the nerfstudio implementation, the expected depth just falls out from the rendering equation (accumulated weights) for...

> Since multiple gaussians are blended to produce each pixel I think the right way to predict depth is likely to use the same factor that is multiplied by the...

This is the optimization process at work. Refer to Sec. 5.2 from the original 3DGS paper. During training, additional points/gaussians are spawned by a series of heuristic optimization steps: splitting,...

Can you update your branch with latest main?

@Siming-He, just one question. Does it make sense to report the "training for 3s, 33s, or 153s" since doesn't the finetuning and amount of seconds highly depend on your computer...

Great, thanks @Siming-He for answering my questions. LGTM, if you update your branch I can merge it!

I see thanks for the issue. `vdbfusion` is a dependency if you want to try out the `gs-mesh tsdf` script. I think removing this dependency from the pyproject.toml installation might...

Hi @Valentina-Zhang, can you use the dedicated `scannetpp` dataparser (instead of `coolermap`) when using scannett data? We use the iPhone depth sequences "b20a261fdf" and "8b5caf3398" from ScanNet++. In the paper...