Depth Attention for Robust RGB Tracking

TL;DR

This paper introduces a novel depth attention mechanism that enhances RGB video object tracking by integrating monocular depth estimation, significantly improving robustness and accuracy without requiring RGB-D cameras.

Contribution

It is the first to propose a depth attention mechanism and a seamless framework for integrating depth with existing tracking algorithms, boosting performance in challenging scenarios.

Findings

Achieves state-of-the-art results on six benchmarks.

Provides consistent improvements over strong baselines.

Demonstrates robustness in motion-blurred and out-of-view tracking.

Abstract

RGB video object tracking is a fundamental task in computer vision. Its effectiveness can be improved using depth information, particularly for handling motion-blurred target. However, depth information is often missing in commonly used tracking benchmarks. In this work, we propose a new framework that leverages monocular depth estimation to counter the challenges of tracking targets that are out of view or affected by motion blur in RGB video sequences. Specifically, our work introduces following contributions. To the best of our knowledge, we are the first to propose a depth attention mechanism and to formulate a simple framework that allows seamlessly integration of depth information with state of the art tracking algorithms, without RGB-D cameras, elevating accuracy and robustness. We provide extensive experiments on six challenging tracking benchmarks. Our results demonstrate that our approach provides consistent gains over several strong baselines and achieves new SOTA performance. We believe that our method will open up new possibilities for more sophisticated VOT solutions in real-world scenarios. Our code and models are publicly released: https://github.com/LiuYuML/Depth-Attention.