taoranyi

Hi! Thanks for your attention. My environment is as follows： Ubuntu 20.04.4 LTS PyTorch version : 1.9.0 CUDA version : 11.1 torch_scatter : 2.0.9

"pip install jax==0.2.20" may solve your problem

It is a good question! This translation filed is referenced in D-nerf Yuo can have a look at this D-nerf code. 

There is indeed an issue here. I have no design to implement rendering without training. I will fix this soon.

Hello, this may actually download the diffusion model weight. After the download is completed, you can start running.

Hello, this may actually download the diffusion model weight or the program crashed. Have you tried to run it again?

Hello, pysdf is not a necessary library, and now I have deleted it.

Hi！ Look this.https://github.com/hustvl/GaussianDreamer/blob/0005b2e87b0605f11579efac0813a7e3bbb28952/threestudio/systems/GaussianDreamer.py#L209

Thank you for your attention. This has a related [question](https://github.com/hustvl/GNeuVox/issues/3#issuecomment-1534648030).

Hello, as you mentioned, a given batch of rays (all 6 patches) comes from an image, and during pre-training, the rays are randomly selected from images of different objects. The...