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.
How do you use the refine mask feature in the webui? Every time I select a frame to refine the mask it gives me a numpy array error when I click to fix the mask. Also, how do we get information about the mask, all it gives currently is a png of the masks but its not in a useful format.
How do you use the refine mask feature in the webui? Every time I select a frame to refine the mask it gives me a numpy array error when I click to fix the mask. Also, how do we get information about the mask, all it gives currently is a png of the masks but its not in a useful format.