yuzy

Hi author, I find that cropped TSDF chunks are used during training/inference, which may introduce wrong scene geometry because of the missing part and affect color prediction. How do you...

Hi, author. I want to render ngp with batch rays origins and batch rays directions. How to perform it with current codes? Could you give me some advice?

Hi author, thx for your amazing repo! When I train on an indoor scene I find nan values appear in the density grid which leads to errors like: > in...

Deformation for view direction?

2

Hi, author! Both nerfies and non-rigid nerf use deformation field. However, in non-rigid nerf they recompute view direction after deformation. How does nerfies deal with it? I quickly reviewed your...

AttributeError when calling restart() of multithreadaugmentor

1

Hi. I write my own dataloader according to your barts173D.py. However, when I run the code, the python will show something like `AttributeError: 'NoneType' object has no attribute 'is_alive' `...

The constrain part in Jacobian mat may be wrong

2

you may loss the derivatives of rotation mat for each vertices in constrain part. https://github.com/JiaxiangZheng/DeformationGraph/blob/b250685dc1485955710c3dfcbc4dc5e0c60e9f0b/src/DeformGraph.cpp#L328

Question about the lemma 1.6 and code implementation

1

Hi. In your paper the lemma 1.6 is talking about the distribution of X and Y=sin(pi/2*X). We have known that the output of linear layer is in normal distribution if...

Dear eladrich, Thx for your great repo! I want to finetune latent nerf as your paper said by changing nerf type from "latent" to "latnet_tune" nad setting optim ckpt path....

How to render SMPLX front and back normal if I konw the camera parameters KRT and SMPLX parameters?

5

Dear author, I want to test your normal net performance with my custom multiview data. Since I have already konwn the camera parameters and SMPLX parameters of the captured human,...

Does the conv in MeshVAE suffer from order problem?

1

Given 2 adjacent faces and denote the intersect edge as e. The adjacent edges of e will be {a, b, c, d}. The conv operation on adjacent edges can be...