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

The equation of Sq Rel #13

Open
Naturallyyeyeye opened this issue Jun 4, 2020 · 1 comment
Open

The equation of Sq Rel #13

Naturallyyeyeye opened this issue Jun 4, 2020 · 1 comment

Comments

@Naturallyyeyeye
Copy link

Naturallyyeyeye commented Jun 4, 2020

What is the equation of sqErrorRel? I test the 1000 images downloaded from "http://www.cvlibs.net/datasets/kitti/eval_depth.php?benchmark=depth_prediction" . When I used the equation provided by Eigen, the result is 0.51187 . However the result provided by KITTI ranking list is 0.042. I am confused that why the difference of the two results is big.
Second,I failed to find the 652 test of Eigen Split from the KITTI Dataset. Can I ask for your help? I am looking forward to your reply.Thank you very much.

@jahaniam
Copy link
Owner

jahaniam commented Jun 7, 2020

You can find eigen test files here : https://github.com/jahaniam/semiDepth/blob/master/utils/filenames/eigen_test_files_withGT.txt

sqErrorRel is a common metric in depth estimation you can find it in Eigen paper:
paper
Note that the kitti benchmark metrics are written at the top of their page and sqErrorRel is in percentage

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

2 participants