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

Cannot reproduce zebra segmentation example with supported codes. #2

Open
dongheon-yoo opened this issue Aug 4, 2019 · 4 comments
Open

Comments

@dongheon-yoo
Copy link

Hi :) First, I'd like to appreciate authors to present sample codes!
As I'm a lot interested in "Double-DIP' structure for image segmentation,
I'm trying to reproduce the results reported in the original paper!
Especially, I'm trying to reproduce zebra segmentation, but I couldn't make it with provided sample codes ("segmentation.py"), same model configurations, network structures, etc.
Could you please check them if the sample codes properly generate reported layer images and the binary mask?
Thanks in advance :)

@abkds
Copy link

abkds commented Sep 25, 2019

Hi authors. I am also interested in using the code for image segmentation I wrote a segment function which looks pretty much similar to dehaze function. But the object created using Segmentation, when I used optimize, asked for a fg_hint or bg_hint. How to pass that ? I mean what should be the value for that?

It would be really nice if you could post a worked example of segmentation of a sample image.
Thanks in advance :)

@yossigandelsman
Copy link
Owner

You can take the saliency from https://cgm.technion.ac.il/Computer-Graphics-Multimedia/Software/Saliency/Saliency.html, and apply a threshold using the code from Github.

@zfy-csu
Copy link

zfy-csu commented Oct 17, 2020

After saliency , the image size will be changed and then the shape of the hint will be different from the origin image.
How you sovle this problem?

@FreyaWan-hub
Copy link

Same problem to me. Can u solve this?

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

5 participants