Tracking Anything in High Quality

TL;DR

HQTrack is a high-quality video object tracking framework that combines a multi-object segmenter and a mask refiner, achieving state-of-the-art results without test-time tricks.

Contribution

The paper introduces HQTrack, a novel framework integrating VMOS and a pretrained mask refiner for improved tracking accuracy in complex scenes.

Findings

Ranks 2nd in VOTS2023 challenge

Effective mask refinement without test-time tricks

Generalizes well to complex and corner scenes

Abstract

Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows the unification of single/multiobject and box/mask-based tracking. Among them, the Segment Anything Model (SAM) attracts much attention. In this report, we propose HQTrack, a framework for High Quality Tracking anything in videos. HQTrack mainly consists of a video multi-object segmenter (VMOS) and a mask refiner (MR). Given the object to be tracked in the initial frame of a video, VMOS propagates the object masks to the current frame. The mask results at this stage are not accurate enough since VMOS is trained on several closeset video object segmentation (VOS) datasets, which has limited ability to generalize to complex and corner scenes. To further improve the quality of tracking masks, a pretrained MR model is employed to refine the tracking results. As a compelling testament to the effectiveness of our paradigm, without employing any tricks such as test-time data augmentations and model ensemble, HQTrack ranks the 2nd place in the Visual Object Tracking and Segmentation (VOTS2023) challenge. Code and models are available at https://github.com/jiawen-zhu/HQTrack.