Meta today announced the release of Segment Anything, a tool that can accurately identify objects in images. The project includes a model, dataset and allows others to use it under a more liberal Apache 2.0 license.
The model is called the Segment Anything Model (SAM), and the dataset is called the Segment Anything 1-Billion mask dataset (SA-1B), which Meta officials say is the largest Segmentation Dataset ever created.
Meta’s official press release that the SAM model can be applied to various fields to find and segment any object in an image.
Developers can build on the model’s technology to develop artificial intelligence with greater functionality and broader reach. In virtual reality (VR) and augmented reality (AR) scenarios, information about objects can be interactively displayed based on the user’s gaze.