search

google / dynibar

Implementation of DynIBaR Neural Dynamic Image-Based Rendering (CVPR 2023)
https://dynibar.github.io/
Apache License 2.0
852 stars 40 forks source link

The training takes forever #43

Open Lwy-1998 opened 1 year ago

Lwy-1998 commented 1 year ago

I set the N_rand to 384 and chunk_size to 512, to make sure it can run on my rtx3090. But the training process is very slow,is there any way to accelerate it?

zhengqili commented 1 year ago

Hi, Unfortunately current method only works well for large N_rand (> 2500 in my opinion), which requires at least 4x 30G GPUs for training usage.