Chen Wang

Understanding AttentionReplace

5

In the `replace_cross_attention` of AttentionReplace, why `attn_replace` is not used? I guess according to the paper, we have to replace `attn_base` with corresponding layers in `attn_replace` Thank you

how to set the p, q in blog-catalog dataset

1

It seems that the default p=1, q=1 is not as good. and the paper didn't specify the actual value, just mentioned 'set p, q to low values'

Zero123plus finetuning code

1

Is it possible to share the finetuning code of zero123plus? I tried to reimplement as the paper using the same batch size and steps, but the results are far from...

How to access the text to 3d functionality?

2

Hi, thanks for the amazing work. Is there any instructions on how to use the text-to-3d functionality?

I tried to set up the docker and run the run_custom.py on the provided milk data with use_gui 0. However, after some running, the code crashes at some point. Since...

Hi authors, thanks for the great work! I am interested in what object categories in omniobject3d did you use for evaluation?

When I tried to render gaussians of a large scene (9 M Gaussians) with the many cameras (20), the latter ones seem to just crash. (I used the same 20...