Question about the dimension of Forward_feat and render_rays in network_composite.py

zju3dv / ENeRF

SIGGRAPH Asia 2022: Code for "Efficient Neural Radiance Fields for Interactive Free-viewpoint Video"

https://zju3dv.github.io/enerf

Other

418 stars 28 forks source link

Question about the dimension of Forward_feat and render_rays in network_composite.py #25

Closed louhz closed 1 year ago

louhz commented 1 year ago

Hi, I am confused about the dimension in Forward_feat and render_rays functions: the B,S,C,H,W, which is different from the traditional 5D B C D H W. I assume the B is batch size and C,H,W are color, height and width. But I am not sure about the meaning of S dimension. Can you offer me some intuition for this dimension?

Thanks!

haotongl commented 1 year ago

Hi, C is the number of feature channels. S is the number of input views (images).

louhz commented 1 year ago

Hi, C is the number of feature channels. S is the number of input views (images).

Thanks!