facebookresearch / facebookresearch/sam2

Segment all the objects of a video

Open
#105 16 comments 12 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
19.9k
Forks
2.5k
PR merge metrics
No merged PRs in 30d

Description

Hi, thanks for the amazing work. I understood that SAM2 is tracking single or multiple objects in a video. Is there any option to predict all the objects of a video without any prompting? If yes, how fast is the prediction?

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.