Justin Fung


> @Justinfungi Hi, Thanks for your contribution! Are the current commits ready or not? @ashawkey Yup, you could merge it first for the precision part. i think it is done....

> > @Justinfungi Hi, Thanks for your contribution! Are the current commits ready or not? > > @ashawkey Yup, you could merge it first for the precision part. i think...

 Only these 4 for the R-precision

I would like to ask what is the difference between using DMT net fine-tune or just simply training and testing

> It's very usual for the result to be like this, because the training SDS loss is calculated on a low resolution NeRF output (usually 64*64). By contrast, DMTet is...

> Yep, it's a two-stage procedure (from coarse to fine) instead of a parrallel one. If you want to train a DMTet from scratch, I recommend you to check out...

> Good question. I also often failed using DMTet lol, it seems the finetuning to be not stable enough. I'm also wondering why this happens. My case is that the...

> Maybe it's related to randomness or prompt, you can try different seeds, or the examples under `scripts` (like this https://github.com/ashawkey/stable-dreamfusion/blob/main/scripts/run2.sh) to check if these prompts can generate good shapes....

Great! i am working on a project using this repo. it is very helpful. if possible, I would like to contribute to it later.