Closed yerfor closed 1 year ago
I just ablated the modifications, and it seems that the additional .float()
in ambient net contributes significantly to the HEAD_PSNR. By contrast, the grid_type or interpolation_type have no obvious improvements.
@yerfor Hi, it's just an updation to keep the code consistent with other projects, and also bug fixing for gridencoder. Thanks for the ablation!
Thanks a lot. Your implementation of Encoders and RayMarching in CUDA is high-efficient and elegant. May I use your implementation in my project GeneFace, to replace the vanilla NeRF implementation?
Of course!
thx!
Thanks for your brilliant work!
I'm interested in the modifications in the latest commit that update the grid encoder, which seems to replace the
tilegrid
tohashgrid
, Can you briefly explain what's the motivation and how you achieve it?Sincerely.