search

zju3dv / clean-pvnet

Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral
Apache License 2.0
400 stars 106 forks source link

How did you convert the original LINEMOD dataset to the format that has posexyz.npy files? #296

Open monajalal opened 10 months ago

monajalal commented 10 months ago

I am struggling to find any sort of documentation that shows how you have converted the original LINEMOD which looks like below:

(clean-pvnet) mona@ada:/data2/data/BOP/lm/train_pbr/000000$ ls
total 8.0M
drwxrwxrwx 52 mona mona 4.0K Jun  1  2020 ..
drwxrwxrwx  6 mona mona 4.0K Oct 11 13:37 .
drwxrwxrwx  2 mona mona  36K Oct 11 13:37 rgb
drwxrwxrwx  2 mona mona  36K Oct 11 13:37 depth
drwxrwxrwx  2 mona mona 552K Oct 11 13:37 mask_visib
drwxrwxrwx  2 mona mona 552K Oct 11 13:37 mask
-rwxrwxrwx  1 mona mona 4.2M Jun  5  2020 scene_gt.json
-rwxrwxrwx  1 mona mona 124K Jun  5  2020 scene_camera.json
-rwxrwxrwx  1 mona mona 2.5M Jun  5  2020 scene_gt_info.json

To a format that has pose files such as below.

(base) mona@DOS:~/Downloads/LINEMOD/cat/pose$ ls | head -5
total 4.7M
drwxrwxr-x  2 mona mona  36K Sep 22  2019 .
-rw-rw-r--  1 mona mona  176 Sep 22  2019 pose9.npy
-rw-rw-r--  1 mona mona  176 Sep 22  2019 pose99.npy
-rw-rw-r--  1 mona mona  176 Sep 22  2019 pose98.npy

Could you please share some thoughts here @pengsida ?