search

rover-xingyu / Ha-NeRF

[CVPR 2022] Ha-NeRF😆: Hallucinated Neural Radiance Fields in the Wild
148 stars 13 forks source link

Sample points for train and test #31

Closed lt-xiang closed 1 year ago

lt-xiang commented 1 year ago

Hi, as the originial NeRF-W said, "During training, 512 points per ray are sampled from each of the coarse and fine models for a total of 1024 points per ray. We double that number during evaluation to 2048."

But the settings are 64(train) and 256(test) in your code. May I ask why there is a difference ?

rover-xingyu commented 1 year ago

Hi! Our training settings are cheaper than the ones used in the original NeRF-W work because of the limited availability of computational resources.