Ego3DT: Tracking Every 3D Object in Ego-centric Videos

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hao, Shengyu, Chai, Wenhao, Zhao, Zhonghan, Sun, Meiqi, Hu, Wendi, Zhou, Jieyang, Zhao, Yixian, Li, Qi, Wang, Yizhou, Li, Xi, Wang, Gaoang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910645303115776
author Hao, Shengyu
Chai, Wenhao
Zhao, Zhonghan
Sun, Meiqi
Hu, Wendi
Zhou, Jieyang
Zhao, Yixian
Li, Qi
Wang, Yizhou
Li, Xi
Wang, Gaoang
author_facet Hao, Shengyu
Chai, Wenhao
Zhao, Zhonghan
Sun, Meiqi
Hu, Wendi
Zhou, Jieyang
Zhao, Yixian
Li, Qi
Wang, Yizhou
Li, Xi
Wang, Gaoang
contents The growing interest in embodied intelligence has brought ego-centric perspectives to contemporary research. One significant challenge within this realm is the accurate localization and tracking of objects in ego-centric videos, primarily due to the substantial variability in viewing angles. Addressing this issue, this paper introduces a novel zero-shot approach for the 3D reconstruction and tracking of all objects from the ego-centric video. We present Ego3DT, a novel framework that initially identifies and extracts detection and segmentation information of objects within the ego environment. Utilizing information from adjacent video frames, Ego3DT dynamically constructs a 3D scene of the ego view using a pre-trained 3D scene reconstruction model. Additionally, we have innovated a dynamic hierarchical association mechanism for creating stable 3D tracking trajectories of objects in ego-centric videos. Moreover, the efficacy of our approach is corroborated by extensive experiments on two newly compiled datasets, with 1.04x - 2.90x in HOTA, showcasing the robustness and accuracy of our method in diverse ego-centric scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08530
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Ego3DT: Tracking Every 3D Object in Ego-centric Videos
Hao, Shengyu
Chai, Wenhao
Zhao, Zhonghan
Sun, Meiqi
Hu, Wendi
Zhou, Jieyang
Zhao, Yixian
Li, Qi
Wang, Yizhou
Li, Xi
Wang, Gaoang
Computer Vision and Pattern Recognition
Multimedia
The growing interest in embodied intelligence has brought ego-centric perspectives to contemporary research. One significant challenge within this realm is the accurate localization and tracking of objects in ego-centric videos, primarily due to the substantial variability in viewing angles. Addressing this issue, this paper introduces a novel zero-shot approach for the 3D reconstruction and tracking of all objects from the ego-centric video. We present Ego3DT, a novel framework that initially identifies and extracts detection and segmentation information of objects within the ego environment. Utilizing information from adjacent video frames, Ego3DT dynamically constructs a 3D scene of the ego view using a pre-trained 3D scene reconstruction model. Additionally, we have innovated a dynamic hierarchical association mechanism for creating stable 3D tracking trajectories of objects in ego-centric videos. Moreover, the efficacy of our approach is corroborated by extensive experiments on two newly compiled datasets, with 1.04x - 2.90x in HOTA, showcasing the robustness and accuracy of our method in diverse ego-centric scenarios.
title Ego3DT: Tracking Every 3D Object in Ego-centric Videos
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2410.08530