Ruizhi Shao

Hi @hrz2000 , I think there are currently two problems. One is that our NeRF model does not support 360-degree scenes. Another issue is that some losses in NeRF, such...

That sounds interesting. I think there is another way to implement this from the perspective of the diffusion model. We can implement a mixture of different diffusion models, namely A,...

Dear Jiakui, We use 3D scan dataset such as THuman2.0 to generate the ground truth disparity maps and train our model. You can apply for the THuman2.0 dataset which is...

Hi, @Konstantysz You can refer to [threestudio-dreamcraft3D](https://github.com/DSaurus/threestudio-dreamcraft3D). We use a new background remover which will not downgrade torch.

Hi, You can use the following config and code to test your diffusion model. ``` system: prompt_processor_type: "stable-diffusion-prompt-processor" prompt_processor: pretrained_model_name_or_path: "stabilityai/stable-diffusion-2-1-base" prompt: "A cute panda" front_threshold: 30. back_threshold: 30. guidance_type:...

> Wow, I just looked at your Control4D project page, the results are amazing! Congratulations and thanks for sharing your code! Hi! Thank you for your kind words. I believe...

I have extended Threestudio to support 3d reconstruction from multi-view images. Here are the reconstruction results on the instructnerf2nerf dataset. https://github.com/threestudio-project/threestudio/assets/24589363/287d2e51-80d1-42e8-b31f-b68767dc7621 Additionally, threestudio now supports the editing of 3D scenes...

Hi, It appears that your gcc is unable to compile nvdiffrast. You need to check out your gcc version and verify if it supports C++17.

Hi! You could also consider using a black background. In my experience, a black background tends to be more stable and avoids issues of over-saturation. Here are my results: Before:...

Hi, guys. @bennyguo @ylhua I have discovered another significant issue, which is opaque loss. In the default configuration, the lambda_opaque will be set to 1000 after 10000 iterations. However, this...