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.
It would be nice to have the web demo compatibile with image sequences input other then Video.
It will be easier to test it on the fly with Davis and YouTube VOS dataset
It would be nice to have the web demo compatibile with image sequences input other then Video. It will be easier to test it on the fly with Davis and YouTube VOS dataset