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

A New Scene Graph Dataset with Segmentation Masks - PSG #3

Open
Jingkang50 opened this issue Aug 30, 2022 · 2 comments
Open

A New Scene Graph Dataset with Segmentation Masks - PSG #3

Jingkang50 opened this issue Aug 30, 2022 · 2 comments

Comments

@Jingkang50
Copy link

Thank you for your nice survey! It really gives good guidance for the community.
However, we notice that in Table 1, the modality of scene graph in COCO is ticked. May I ask where is the COCO scene graph comes from? Actually, our recent work PSG provides a high-quality scene graph annotation based on COCO panoptic segmentation, so that Semantic Map, Bounding Box, Text, Scene Graph are all available in the PSG dataset.

You could get the general idea of PSG dataset by glancing our codebase or interactively explore the dataset on our website.
We would really appreciate if the PSG dataset could be included in the table and contribute to the image editing community.

Screenshot 2022-08-30 at 1 59 46 PM

@Jingkang50 Jingkang50 changed the title A New Scene Graph Dataset with Masks - PSG A New Scene Graph Dataset with Segmentation Masks - PSG Aug 30, 2022
@fnzhan
Copy link
Owner

fnzhan commented Aug 30, 2022

Thanks for sharing the information and your awesome dataset. We find there is a typo when retrieving the information from Table 1 of 'Deep Image Synthesis from Intuitive User Input: A Review and Perspectives'. COCO-Stuff should be ticked instead of COCO, we will correct it in the table and also include your dataset in the table.

@Jingkang50
Copy link
Author

Cool, that makes sense. Thank you Dr. Zhan for your clarification!

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