New Delhi: Meta has unveiled its Segment Anything Model 3, also known as SAM 3, which is the next generation of visual understanding tools. The latest model includes some significant improvements in object detection, segmentation, and tracking across images and videos. Users can now use the text-based and exemplar prompts to identify and segment almost any visual concept. Meta has also unveiled the Segment Anything Playground. This latest interface allows the general public to experiment with SAM 3 and test its media editing capabilities without the need for technical knowledge.
Today we’re excited to unveil a new generation of Segment Anything Models:
1️⃣ SAM 3 enables detecting, segmenting and tracking of objects across images and videos, now with short text phrases and exemplar prompts.
🔗 Learn more about SAM 3: https://t.co/tIwymSSD89
2️⃣ SAM 3D… pic.twitter.com/kSQuEmwH33
— AI at Meta (@AIatMeta) November 19, 2025
The company will also be releasing model weights, a detailed research paper, and the latest evaluation benchmark called SA-Co to assist the developers working on open-vocabulary segmentations. Meta is also going to release the SAM 3D, a collection of models capable of object and scene reconstruction, as well as human pose and shape estimation, with applications in augmented reality, robotics, and other spatial computing fields. SAM 3 introduces the promptable concept segmentation, which allows the model to segment anything users describe using short noun phrases or image examples.
Meta has also claimed that SAM 3 outperforms previous systems on its latest SA-Co benchmark for both images and video. The model accepts a variety of prompts, such as masks, bounding boxes, points, text, and image examples, giving the users multiple options for specifying what they want to detect or track. The latest model was trained using the large-scale data pipeline that included human annotators, SAM 3 and supporting AI systems like a Llama-based captioner.
It processes and labels visual data much more efficiently than the traditional methods, reducing the annotation time and enabling the creation of a dataset of over 4 million visual concepts. Meta has already used the SAM 3 and SAM 3D to power features like View in Room on Facebook Marketplace, which enables customers to see furniture in their own homes. The technology will also be integrated into upcoming visual editing tools on the Meta AI and editing applications.
