Segment and Track Anything

TL;DR

SAMTrack is a versatile framework that combines segmentation and tracking in videos using multimodal interactions, enabling precise object tracking across various fields with high accuracy and user-friendly controls.

Contribution

The paper introduces SAMTrack, integrating SAM, AOT-based tracking, and Grounding-DINO for multimodal, interactive object segmentation and tracking in videos, achieving state-of-the-art performance.

Findings

Achieved 92.0% on DAVIS-2016 Val

Achieved 79.2% on DAVIS-2017 Test

Supports multiple interaction modes (click, stroke, text)

Abstract

This report presents a framework called Segment And Track Anything (SAMTrack) that allows users to precisely and effectively segment and track any object in a video. Additionally, SAM-Track employs multimodal interaction methods that enable users to select multiple objects in videos for tracking, corresponding to their specific requirements. These interaction methods comprise click, stroke, and text, each possessing unique benefits and capable of being employed in combination. As a result, SAM-Track can be used across an array of fields, ranging from drone technology, autonomous driving, medical imaging, augmented reality, to biological analysis. SAM-Track amalgamates Segment Anything Model (SAM), an interactive key-frame segmentation model, with our proposed AOT-based tracking model (DeAOT), which secured 1st place in four tracks of the VOT 2022 challenge, to facilitate object tracking in video. In addition, SAM-Track incorporates Grounding-DINO, which enables the framework to support text-based interaction. We have demonstrated the remarkable capabilities of SAM-Track on DAVIS-2016 Val (92.0%), DAVIS-2017 Test (79.2%)and its practicability in diverse applications. The project page is available at: https://github.com/z-x-yang/Segment-and-Track-Anything.