zparquet / fast-learning Goto Github PK

May I ask if the framework you have developed is integrated with some of the latest NeRF technologies this year, such as TriMIP NeRF? How effective is it?

I want to reproduce the results of the paper for running with instant NGP dataset on LLFF and Nerf Synthetic dataset. I run the following command as per your readme:

python main_nerf.py data/nerf_synthetic/lego --workspace trial_nerf -O --bound 1.0 --scale 0.8 --dt_gamma 0

However I notice that none of the functions in quadtree are being called and the image_probs is the same all over. Am I running it with the wrong setup?

If I uncomment the following line in provider.py:
self.image_probs.append(get_img_prob(image))
I get an error (during get_img_prob).

Can you please help me find the correct setup for running your code vs. uniform sampling?

Thank you