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

optical flow with superpixel #1

Closed
xiaofanglegoc opened this issue Sep 13, 2018 · 4 comments
Closed

optical flow with superpixel #1

xiaofanglegoc opened this issue Sep 13, 2018 · 4 comments

Comments

@xiaofanglegoc
Copy link

Thank you for the release of project, and it is a great work!

In your paper, there are a section on the optical flow using SSN_{deep}, which gives a good visual results, would you please give some hints or demo on this part ?

@pinkfloyd06
Copy link

Hello,

Thank you for this work. I'm also interested on this part

@varunjampani
Copy link
Contributor

I am currently on travel. I will add the sintel trained model in 'get_models.sh' script after a couple of weeks. You can use that model to obtain superpixels on sintel images using 'compute_ssn_spixels.py` script. Or, are you interested in visualization of segmented flow given the superpixels?

@xiaofanglegoc
Copy link
Author

thanks wait for your upate

@varunjampani
Copy link
Contributor

I have added 'ssn_sintel_model.caffemodel' to 'get_models.sh'. You can use this caffemodel with the 'compute_ssn_spixels.py' script to obtain superpixels on sintel images:

python compute_ssn_spixels.py --datatype SINTEL_VAL --n_spixels 100 --num_steps 10 --caffemodel ./models/ssn_sintel_model.caffemodel --is_connected False --result_dir ./sintel_val_100/

You need to add corresponding image list and image folder locations to 'config.py'.

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

3 participants