Liam Schoneveld

This is a question about the method/paper, not so much the implementation. During training, do you provide the corresponding camera pose (denoted as ξ in the paper) to the discriminator?...

Expected values of `ins_prob` and `ins_loss` in MoCo when training is working

1

Hi there Thanks a lot for this great repo! I am trying out MoCo on my own dataset (I also added additional augmentations). Training appears to have converged, but the...

Hi there Great work on this repo / paper! I would like to extend it possibly. Would it be possible for you to upload the weights to another location? I...

Error when trying to train a model with masks

1

**Describe the bug** When training a `nerfacto` model on data whose `transforms.json` contains `mask_path`s (i.e., I have corresponding masks for all images), I get an error that ends in the...

Hi there Thanks for this great repo! Just wondering - how did you get the dataset with 296 people. On the RenderPeople website link you include in the README, it...

Any tips for training on my own dataset / fixing scale from COLMAP?

6

Hi there, First of all, thanks for releasing the code for this impressive method! I have been trying to train this on my own dataset (it's front-facing). After a bit...

This PR modifies FullyFusedProjection and FullyFusedProjection2DGS such that the intrinsics (`Ks`) receive gradients. Am currently working on adding it to PackedProjection as well Inspiration and derivation of gradients to K...

`rasterization_2dgs` rendering no longer works when `sh_degree=None` as of v1.5.3

2

Note: this only appears to affect 2DGS, not 3DGS ! After `pip install git+https://github.com/nerfstudio-project/[email protected]` Taking the example from `rasterization_2dgs` docstring: ```python from gsplat import rasterization_2dgs import torch device = "cuda"...

Hello Thank you for releasing this great work! I have been playing around with it and have a question: If we assume the FOV estimator makes a correct FOV prediction...