Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Huiming, Liao, Linglin, Ding, Fei, Wang, Sibo, Zeng, Zijian
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.22979
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918268276572160
author Yang, Huiming
Liao, Linglin
Ding, Fei
Wang, Sibo
Zeng, Zijian
author_facet Yang, Huiming
Liao, Linglin
Ding, Fei
Wang, Sibo
Zeng, Zijian
contents Six degree of freedom (6DoF) pose estimation for novel objects is a critical task in computer vision, yet it faces significant challenges in high-speed and low-light scenarios where standard RGB cameras suffer from motion blur. While event cameras offer a promising solution due to their high temporal resolution, current 6DoF pose estimation methods typically yield suboptimal performance in high-speed object moving scenarios. To address this gap, we propose PoseStreamer, a robust multi-modal 6DoF pose estimation framework designed specifically on high-speed moving scenarios. Our approach integrates three core components: an Adaptive Pose Memory Queue that utilizes historical orientation cues for temporal consistency, an Object-centric 2D Tracker that provides strong 2D priors to boost 3D center recall, and a Ray Pose Filter for geometric refinement along camera rays. Furthermore, we introduce MoCapCube6D, a novel multi-modal dataset constructed to benchmark performance under rapid motion. Extensive experiments demonstrate that PoseStreamer not only achieves superior accuracy in high-speed moving scenarios, but also exhibits strong generalizability as a template-free framework for unseen moving objects.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22979
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PoseStreamer: A Multi-modal Framework for 3D Tracking of Unseen Moving Objects
Yang, Huiming
Liao, Linglin
Ding, Fei
Wang, Sibo
Zeng, Zijian
Computer Vision and Pattern Recognition
Six degree of freedom (6DoF) pose estimation for novel objects is a critical task in computer vision, yet it faces significant challenges in high-speed and low-light scenarios where standard RGB cameras suffer from motion blur. While event cameras offer a promising solution due to their high temporal resolution, current 6DoF pose estimation methods typically yield suboptimal performance in high-speed object moving scenarios. To address this gap, we propose PoseStreamer, a robust multi-modal 6DoF pose estimation framework designed specifically on high-speed moving scenarios. Our approach integrates three core components: an Adaptive Pose Memory Queue that utilizes historical orientation cues for temporal consistency, an Object-centric 2D Tracker that provides strong 2D priors to boost 3D center recall, and a Ray Pose Filter for geometric refinement along camera rays. Furthermore, we introduce MoCapCube6D, a novel multi-modal dataset constructed to benchmark performance under rapid motion. Extensive experiments demonstrate that PoseStreamer not only achieves superior accuracy in high-speed moving scenarios, but also exhibits strong generalizability as a template-free framework for unseen moving objects.
title PoseStreamer: A Multi-modal Framework for 3D Tracking of Unseen Moving Objects
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.22979