facebookresearch / facebookresearch/sam2
When the bbox is large, the segmentation results become chaotic.
Open
- Dominant language
- Jupyter Notebook
- Stars
- 19.9k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
First of all, thank you for such an excellent open-source project!
I tried segmenting the image with a given bbox, but the segmentation results are quite chaotic, making it difficult for me to extract a good boundary based on the results. Could you please advise if there are any parameters or methods that could help alleviate this issue?
Contributor guide
Assessment
This issue has not been assessed yet.