Christopher Wewer

Results 6 comments of Christopher Wewer

Thanks for your quick answer. I think, aligning the indexing to the regular one on dense tensors is definetly important regarding your "ultimate long-term goal". In my case, I noticed...

Thank you for your quick response. I have another question regarding the way how you calculate the random walk matrix for the DCGRUCell: You first add the identity to the...

Hello, thanks for your great work. Are there any updates regarding PeRFception-CO3D-v2? I would like to use it as well!

Hi, sorry for the late response. The config files are exactly the ones given in the repository and command `python3 -m src.main +experiment=co3d_hydrant` you mentioned is correct. Have you trained...

Hi @botev , I face exactly the same (original) problem. Did you find any solution?

Hi, sorry for the late response. It is correct that we first train only with the target_render_image loss for the first 100k iterations, because the rough geometry should be correct,...