Track Anything: Segment Anything Meets Videos

TL;DR

This paper introduces the Track Anything Model (TAM), which extends the Segment Anything Model (SAM) for high-performance, interactive video object tracking and segmentation with minimal human input, without additional training.

Contribution

The paper presents TAM, a novel extension of SAM that enables effective interactive tracking and segmentation in videos with minimal human clicks, without requiring extra training.

Findings

Achieves high-quality video segmentation with few human clicks

Operates effectively without additional training

Facilitates interactive video object tracking and segmentation

Abstract

Recently, the Segment Anything Model (SAM) gains lots of attention rapidly due to its impressive segmentation performance on images. Regarding its strong ability on image segmentation and high interactivity with different prompts, we found that it performs poorly on consistent segmentation in videos. Therefore, in this report, we propose Track Anything Model (TAM), which achieves high-performance interactive tracking and segmentation in videos. To be detailed, given a video sequence, only with very little human participation, i.e., several clicks, people can track anything they are interested in, and get satisfactory results in one-pass inference. Without additional training, such an interactive design performs impressively on video object tracking and segmentation. All resources are available on {https://github.com/gaomingqi/Track-Anything}. We hope this work can facilitate related research.