Ethan Weber

> I have the same question. Also the result of running `semantic-nerfw` on `friends` dataset using default settings doesn't look good. I don't expect the results to look good until...

Hi @h8c2, thanks for noting this. Do you imagine that [this function call](https://github.com/nerfstudio-project/nerfstudio/blob/3da877050df2c9b347652a5a84ad6d5d8c768650/nerfstudio/models/depth_nerfacto.py#L83) should look at `termination_depth` and mask out regions where GT depths == 0 in the loss? We...

Hey @lkskstlr, we are refactoring the dataloader and then we will merge PR #961. It's quite a big change, so we just want to make sure it doesn't break anything....

@terrancewang I'd try to structure this implementation as a Pipeline since the Model (with Fields) should be largely agnostic to DreamFusion. We should be able to swap out Models that...

@devernay thanks for the comments! We agree with you. I've removed nvdiffrast from the repo and am using PyTorch instead without additional libraries. It's a bit slower but I had...

@machenmusik Good catch. We need to predict normals for poisson meshing to work well. We're still debating whether to default to predicting normals or not going forward. TSDF meshing will...

I agree with your comments @machenmusik and will make the changes to have better defaults and documentation. Thanks for the thoughts!

I think it might make sense to have a separate function for rasterize 4-dim. We have a rasterize 3-dim (for rgb) and N-dim, but we could also have one for...

@nikmo33 Interesting, I'll have to check out your new code. Is the current code in Splatfacto incorrect with its gradients after dividing out alpha?

Hi @maturk and @nikmo33, I'm quite interested in this feature now too. Let me know if I can help out somewhere, or what the timeline looks like. :)