HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback

TL;DR

HQ-SMem introduces a memory-efficient, self-supervised video segmentation and tracking method that enhances boundary accuracy, handles complex object transformations, and maintains robustness over long videos.

Contribution

The paper presents a novel approach combining high-quality mask refinement, selective memory updates, and dynamic appearance modeling to improve VOS performance.

Findings

Outperforms state-of-the-art on VOTS and VOTSt 2024 datasets.

Sets new benchmarks on Long Video Dataset and LVOS.

Effectively handles complex multi-object dynamics and long-term video challenges.

Abstract

Video Object Segmentation (VOS) is foundational to numerous computer vision applications, including surveillance, autonomous driving, robotics and generative video editing. However, existing VOS models often struggle with precise mask delineation, deformable objects, topologically transforming objects, tracking drift and long video sequences. In this paper, we introduce HQ-SMem, for High Quality video segmentation and tracking using Smart Memory, a novel method that enhances the performance of VOS base models by addressing these limitations. Our approach incorporates three key innovations: (i) leveraging SAM with High-Quality masks (SAM-HQ) alongside appearance-based candidate-selection to refine coarse segmentation masks, resulting in improved object boundaries; (ii) implementing a dynamic smart memory mechanism that selectively stores relevant key frames while discarding redundant ones, thereby optimizing memory usage and processing efficiency for long-term videos; and (iii) dynamically updating the appearance model to effectively handle complex topological object variations and reduce drift throughout the video. These contributions mitigate several limitations of existing VOS models including, coarse segmentations that mix-in background pixels, fixed memory update schedules, brittleness to drift and occlusions, and prompt ambiguity issues associated with SAM. Extensive experiments conducted on multiple public datasets and state-of-the-art base trackers demonstrate that our method consistently ranks among the top two on VOTS and VOTSt 2024 datasets. Moreover, HQ-SMem sets new benchmarks on Long Video Dataset and LVOS, showcasing its effectiveness in challenging scenarios characterized by complex multi-object dynamics over extended temporal durations.