Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Bad results on LLFF dataset #38

Open
Beniko95J opened this issue Sep 5, 2022 · 0 comments
Open

Bad results on LLFF dataset #38

Beniko95J opened this issue Sep 5, 2022 · 0 comments

Comments

@Beniko95J
Copy link

Beniko95J commented Sep 5, 2022

Hi, I tried to test NerfingMVS on LLFF dataset but get bad results. For example, on scene horns in LLFF dataset, the orignal NeRF gets PSNR=28.85 while NerfingMVS only gets PSNR=19.41. One rendered test image looks like this:
000_nerf

My config file for this scene is:

expname = horns_test
basedir = ./logs
datadir = ./raw_data/horns

factor = 8

N_rand = 1024
N_samples = 64

use_viewdirs = True
raw_noise_std = 1e0

depth_H = 384
depth_W = 512

May I ask for your results on this scene if you have tested it before? I am curious why the performance looks so bad on this scene.

Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant