Zujing Liu
Zujing Liu
I am quite curious about the effect of point-nerf for unbounded scene, such as the Playground/Train (T&T) with large area of sky. So I want to give it a try,...
Hey! Thanks for your works! I tried to run DTU without mask, and 'neus-dtu.yaml' is used. However, the mesh is not good as expected.  It can be seen that...
I tried `bakedangelo` in mipnerf360-byclce, and i set the [scene_scale](https://github.com/autonomousvision/sdfstudio/blob/370902a10dbef08cb3fe4391bd3ed1e227b5c165/nerfstudio/data/dataparsers/mipnerf360_dataparser.py#L54) in mipnerf 360 to make it learn the background mesh. And it only trained for 180k iters because of the...
As mentioned in the title, I do these experiment in mipnerf360 bicycle. I know that the numerical gradient will slow down the training, but why the convergence is slow too?...
Hi, I am trying to the the function `get_surface_sliding() ` in `utils.marching_cubes` to extract mesh for my own project. However, I always get a voxel-like mesh no matter how i...
Hi! Thanks for brilliant work! Do you plan to implement the color regularization in PermutoSDF? I don't seem to find this part of the implementation in the current code. I...
Hi! Thanks for your inspiring work! I plan to try `torch-ash` in outdoor large-scale/unbounded scene. But there is no instruction for custom dataset. So I'm going to go out on...
Hi! Thanks for your great work! Im a little confused about the implementation. Your simple and efficient work only requires once forward caculate to get the activation of each layer....
Hi! Thanks for your brilliant contribution to the community! I was trying to run `TextNeedleInAHaystack` and `ImageNeedleInAHaystack` with llava-v1.5-7b. I notice that the results shown in your paper is both...
I want to utilize the `VanillaDataManager`(nerfstudio-0.2.2) as a component of my work. Now single gpu training works well, and im try to make it in multi-gpu for parallel training. However,...