Entity icon indicating copy to clipboard operation
Entity copied to clipboard

EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation

Results 38 Entity issues
Sort by recently updated
recently updated
newest added

Hi! I wonder how many and what kinds of GPUs did you use in UniGS? How long does the training process take? Thanks!

Hi,I am interested in your this paper, but I have some question. Can you explain the pseudo-label dataset generation stage? How to calculated the score of any prediction and (constant)score...

Thanks for your work。Can the Cropformer-Swin model be converted to tensorRT? How can I improve the speed of predict? I am currently testing 50 images using NVIDIA GeForce RTX 3090,...

作者您好: 很高兴看到您的UniGS论文被cvpr 2024接收,我对您这篇工作比较好奇和感兴趣,特别生成和分割统一表示的部分以及之前您做过的高质量分割,请问啥时候可以开源下代码~

Hello, thanks for your great work! I have a question about the model parameter amount of the CRM model. You declared in your paper that the params are 9.27M. ![image](https://github.com/user-attachments/assets/f5ca6d5f-f304-4b65-bf19-e99f09fa9492)...

Hi, in UniGS, you used SAM for entity segmentation. As for SAM auto mask generation mode, the output masks will have overlapping areas. May I ask how to deal with...

Hello, may I ask when the code for the article 'UniGS: Unified Representation for Image Generation and Segmentation (Arxiv)' will be released?

I have a doubt related to how you have trained the model for semantic segmentation. Have you used the images high res or low res, since the annotations for this...