SAM 2 (Segment Anything Model 2) from Meta is a foundation model for promptable visual segmentation in images and videos. The hiera-base-plus variant supports automatic mask generation, point clicks, bounding boxes, and multi-object tracking across video frames. It is distributed as open weights on Hugging Face and integrates with the Transformers library for research and application development.
Sam2 Hiera Base Plus is an Other AI project. It focuses on performing promptable object segmentation in both images and videos using a single unified model. It is built as an open-source project for machine learning engineers. The project is open source (Open Source). It runs on the web and API.
It is developed by Meta AI (United States), and it first shipped in 2024. Key capabilities include Mask Generation, Video Segmentation, and Point Prompting.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do