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

Decompress depth and depth confidence #11

Open
Yang-Li-2000 opened this issue Apr 30, 2023 · 1 comment
Open

Decompress depth and depth confidence #11

Yang-Li-2000 opened this issue Apr 30, 2023 · 1 comment

Comments

@Yang-Li-2000
Copy link

Yang-Li-2000 commented Apr 30, 2023

How can I decompress depth and depth confidence files with .zlib suffixes?

@SamMaoYS
Copy link
Collaborator

SamMaoYS commented May 1, 2023

Hi @Yang-Li-2000, to decompress the depth and confidence .zlib files, you can use this script server/scripts/depth_decode.py.

This script decompress the depth and confidence streams to png image files. For example, you can use the script with command:

python depth_decode.py -in path/to/scanID.depth.zlib -in_confi path/to/scanID.confidence.zlib -o ./depth -o_confi ./confidence -TH 0 -L 0 -M 0 --format .png

where -TH is the depth delta threshold for consecutive depth frames, -L is the confidence threshold for depth maps, -M is the output mode, 0 mode is output raw decompressed data, 1 mode for output color mapped images
You can find more information in the descriptions for each argument in the script.

If you have the processing server pipeline setup, you can use the scan processing script server/scan_processor.py to get the RGB and depth maps described in the paper, where the depth map is preprocessed to keep only the high confident depth values:

python scan_processor.py process.input_path=path/to/scan_folder  process.overwrite=false process.actions='[convert]'

Thank you for your interest.

All the best,
Yongsen Mao

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