Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Jianqiu, Zhou, Zikun, Sun, Mingshan, Bao, Tianpeng, Zhao, Rui, Wu, Liwei, He, Zhenyu
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2305.17934
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914959226568704
author Chen, Jianqiu
Zhou, Zikun
Sun, Mingshan
Bao, Tianpeng
Zhao, Rui
Wu, Liwei
He, Zhenyu
author_facet Chen, Jianqiu
Zhou, Zikun
Sun, Mingshan
Bao, Tianpeng
Zhao, Rui
Wu, Liwei
He, Zhenyu
contents Many robotics and industry applications have a high demand for the capability to estimate the 6D pose of novel objects from the cluttered scene. However, existing classic pose estimation methods are object-specific, which can only handle the specific objects seen during training. When applied to a novel object, these methods necessitate a cumbersome onboarding process, which involves extensive dataset preparation and model retraining. The extensive duration and resource consumption of onboarding limit their practicality in real-world applications. In this paper, we introduce ZeroPose, a novel zero-shot framework that performs pose estimation following a Discovery-Orientation-Registration (DOR) inference pipeline. This framework generalizes to novel objects without requiring model retraining. Given the CAD model of a novel object, ZeroPose enables in seconds onboarding time to extract visual and geometric embeddings from the CAD model as a prompt. With the prompting of the above embeddings, DOR can discover all related instances and estimate their 6D poses without additional human interaction or presupposing scene conditions. Compared with existing zero-shot methods solved by the render-and-compare paradigm, the DOR pipeline formulates the object pose estimation into a feature-matching problem, which avoids time-consuming online rendering and improves efficiency. Experimental results on the seven datasets show that ZeroPose as a zero-shot method achieves comparable performance with object-specific training methods and outperforms the state-of-the-art zero-shot method with 50x inference speed improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2305_17934
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenes
Chen, Jianqiu
Zhou, Zikun
Sun, Mingshan
Bao, Tianpeng
Zhao, Rui
Wu, Liwei
He, Zhenyu
Computer Vision and Pattern Recognition
Many robotics and industry applications have a high demand for the capability to estimate the 6D pose of novel objects from the cluttered scene. However, existing classic pose estimation methods are object-specific, which can only handle the specific objects seen during training. When applied to a novel object, these methods necessitate a cumbersome onboarding process, which involves extensive dataset preparation and model retraining. The extensive duration and resource consumption of onboarding limit their practicality in real-world applications. In this paper, we introduce ZeroPose, a novel zero-shot framework that performs pose estimation following a Discovery-Orientation-Registration (DOR) inference pipeline. This framework generalizes to novel objects without requiring model retraining. Given the CAD model of a novel object, ZeroPose enables in seconds onboarding time to extract visual and geometric embeddings from the CAD model as a prompt. With the prompting of the above embeddings, DOR can discover all related instances and estimate their 6D poses without additional human interaction or presupposing scene conditions. Compared with existing zero-shot methods solved by the render-and-compare paradigm, the DOR pipeline formulates the object pose estimation into a feature-matching problem, which avoids time-consuming online rendering and improves efficiency. Experimental results on the seven datasets show that ZeroPose as a zero-shot method achieves comparable performance with object-specific training methods and outperforms the state-of-the-art zero-shot method with 50x inference speed improvement.
title ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2305.17934