Hello! Great work in this repository, I find this to be a much more natural use case for SAM2.
The original SAM2 repo has support for using an existing mask as a prompt for video segmentation via the add_new_mask() method, could this be implemented in your real time version?
Hello! Great work in this repository, I find this to be a much more natural use case for SAM2.
The original SAM2 repo has support for using an existing mask as a prompt for video segmentation via the add_new_mask() method, could this be implemented in your real time version?