The follow-up paper, "SAM 2: Segment Anything in Images and Videos," extends the model to handle video objects in real-time.

The first paper, "Segment Anything," introduced the concept of a promptable segmentation system and the massive SA-1B dataset.

If you're asking about the , you're likely looking for the foundational research papers from Meta AI that introduced these computer vision models. Foundational Research Papers

Newsletter signup

    Book an Engineer

    Collection Day
    Computer / Laptop
    Brand
    Operating System
    First name

    Last name

    Email address

    Contact phone number

    Address

    City

    Special requests

    Make an Appointment