3D-Aware Instance Segmentation and Tracking in Egocentric Videos

TL;DR

This paper presents a 3D-aware method for instance segmentation and tracking in egocentric videos, significantly improving accuracy and consistency over existing 2D approaches by leveraging scene geometry and temporal cues.

Contribution

It introduces a novel 3D-aware framework that integrates scene geometry and object tracking for robust egocentric video analysis, outperforming state-of-the-art methods.

Findings

Outperforms previous methods by 7 points in Association Accuracy.

Reduces ID switches by 73-80%.

Enhances downstream 3D reconstruction and amodal segmentation.

Abstract

Egocentric videos present unique challenges for 3D scene understanding due to rapid camera motion, frequent object occlusions, and limited object visibility. This paper introduces a novel approach to instance segmentation and tracking in first-person video that leverages 3D awareness to overcome these obstacles. Our method integrates scene geometry, 3D object centroid tracking, and instance segmentation to create a robust framework for analyzing dynamic egocentric scenes. By incorporating spatial and temporal cues, we achieve superior performance compared to state-of-the-art 2D approaches. Extensive evaluations on the challenging EPIC Fields dataset demonstrate significant improvements across a range of tracking and segmentation consistency metrics. Specifically, our method outperforms the next best performing approach by $7$ points in Association Accuracy (AssA) and $4.5$ points in IDF1 score, while reducing the number of ID switches by $73\%$ to $80\%$ across various object categories. Leveraging our tracked instance segmentations, we showcase downstream applications in 3D object reconstruction and amodal video object segmentation in these egocentric settings.