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

Wrong Predictions using custom Images #7

Open
marcomiglionico94 opened this issue Oct 20, 2021 · 6 comments
Open

Wrong Predictions using custom Images #7

marcomiglionico94 opened this issue Oct 20, 2021 · 6 comments
Labels
enhancement New feature or request question Further information is requested

Comments

@marcomiglionico94
Copy link

marcomiglionico94 commented Oct 20, 2021

I tried to use the Structured 3D pretrained model on some custom images taken from my phone and online.
I noticed that the prediction are not very correct and I wanted to know if there is any preprocessing step that needs to be done on the images. Here are some results I obtained:

0_select (2)

0_select (3)

Any help would be appreciated

@bertjiazheng
Copy link
Collaborator

Hi @marcomiglionico94,

Thanks for your interest in our work! A common failure mode of our approach (as discussed in Section 4.4 of our paper) is that the ceiling-wall and floor-wall boundaries are not precisely localized. The reason is clear since our method does not explicitly detect these two boundaries.

Best,
Jia

@bertjiazheng bertjiazheng added the question Further information is requested label Oct 21, 2021
@marcomiglionico94
Copy link
Author

Thanks @bertjiazheng any ideas of how we can visualize it in 3 dimensions like you did in the paper?
Thanks,
Marco

@bertjiazheng
Copy link
Collaborator

bertjiazheng commented Oct 22, 2021

I will add this feature (same as #1) ASAP.

Best,
Jia

@bertjiazheng bertjiazheng added the enhancement New feature or request label Oct 22, 2021
@marcomiglionico94
Copy link
Author

Great @bertjiazheng, thanks a lot

@marcomiglionico94
Copy link
Author

I will add this feature (same as #1) ASAP.

Best, Jia

Hi any updates on this?

@HardikJain02
Copy link

I will add this feature (same as #1) ASAP.

Best, Jia

Any plan to publish? If not, you can tell the approach or publish the messy code.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request question Further information is requested
Projects
None yet
Development

No branches or pull requests

3 participants