search

chenhsuanlin / bundle-adjusting-NeRF

BARF: Bundle-Adjusting Neural Radiance Fields 🤮 (ICCV 2021 oral)
MIT License
793 stars 114 forks source link

how to visualize positional encoding in visdom? #55

Closed thekaka closed 2 years ago

thekaka commented 2 years ago

Figure 5 in the paper shows NeRF naive postinal encoding result, which displays the GT pose and refine pose of full postional encoding.

I looked into nerf part codes, but there is no relevant ones.

https://github.com/chenhsuanlin/bundle-adjusting-NeRF/blob/803291bd0ee91c7c13fb5cc42195383c5ade7d15/model/nerf.py#L89

Visulization function in nerf.py only supports Tensorbord but not includes visdom like barf.py.

It would be great if you could provide some suggestion about this issue. thx a lot

chenhsuanlin commented 2 years ago

Hi @thekaka, nerf.py in the codebase is for NeRF where cameras are fixed and non-optimizable. For the full positional encoding baseline, please use barf.py without the --barf_c2f argument (see README for more details).