An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.
GNU Affero General Public License v3.0
2.75k
stars
332
forks
source link
How to run the model on custom videos, which have different resolution. How can we change the resolution size? #157
Hey, authors @yamy-cheng @z-x-yang, amazing work; I was just curious what to change for the model to accept custom video to test. Please let me know.