UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Xingyu, Wang, Gu, Zhang, Ruida, Zhang, Chenyangguang, Tombari, Federico, Ji, Xiangyang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912278249472000
author Liu, Xingyu
Wang, Gu
Zhang, Ruida
Zhang, Chenyangguang
Tombari, Federico
Ji, Xiangyang
author_facet Liu, Xingyu
Wang, Gu
Zhang, Ruida
Zhang, Chenyangguang
Tombari, Federico
Ji, Xiangyang
contents Unseen object pose estimation methods often rely on CAD models or multiple reference views, making the onboarding stage costly. To simplify reference acquisition, we aim to estimate the unseen object's pose through a single unposed RGB-D reference image. While previous works leverage reference images as pose anchors to limit the range of relative pose, our scenario presents significant challenges since the relative transformation could vary across the entire SE(3) space. Moreover, factors like occlusion, sensor noise, and extreme geometry could result in low viewpoint overlap. To address these challenges, we present a novel approach and benchmark, termed UNOPose, for unseen one-reference-based object pose estimation. Building upon a coarse-to-fine paradigm, UNOPose constructs an SE(3)-invariant reference frame to standardize object representation despite pose and size variations. To alleviate small overlap across viewpoints, we recalibrate the weight of each correspondence based on its predicted likelihood of being within the overlapping region. Evaluated on our proposed benchmark based on the BOP Challenge, UNOPose demonstrates superior performance, significantly outperforming traditional and learning-based methods in the one-reference setting and remaining competitive with CAD-model-based methods. The code and dataset are available at https://github.com/shanice-l/UNOPose.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16106
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image
Liu, Xingyu
Wang, Gu
Zhang, Ruida
Zhang, Chenyangguang
Tombari, Federico
Ji, Xiangyang
Computer Vision and Pattern Recognition
Unseen object pose estimation methods often rely on CAD models or multiple reference views, making the onboarding stage costly. To simplify reference acquisition, we aim to estimate the unseen object's pose through a single unposed RGB-D reference image. While previous works leverage reference images as pose anchors to limit the range of relative pose, our scenario presents significant challenges since the relative transformation could vary across the entire SE(3) space. Moreover, factors like occlusion, sensor noise, and extreme geometry could result in low viewpoint overlap. To address these challenges, we present a novel approach and benchmark, termed UNOPose, for unseen one-reference-based object pose estimation. Building upon a coarse-to-fine paradigm, UNOPose constructs an SE(3)-invariant reference frame to standardize object representation despite pose and size variations. To alleviate small overlap across viewpoints, we recalibrate the weight of each correspondence based on its predicted likelihood of being within the overlapping region. Evaluated on our proposed benchmark based on the BOP Challenge, UNOPose demonstrates superior performance, significantly outperforming traditional and learning-based methods in the one-reference setting and remaining competitive with CAD-model-based methods. The code and dataset are available at https://github.com/shanice-l/UNOPose.
title UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.16106