Exploring 6D Object Pose Estimation with Deformation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Zhiqiang, Song, Rui, Chuangqi, Duanmu, Li, Jiaojiao, Ferstl, David, Hu, Yinlin
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909030573670400
author Liu, Zhiqiang
Song, Rui
Chuangqi, Duanmu
Li, Jiaojiao
Ferstl, David
Hu, Yinlin
author_facet Liu, Zhiqiang
Song, Rui
Chuangqi, Duanmu
Li, Jiaojiao
Ferstl, David
Hu, Yinlin
contents We present DeSOPE, a large-scale dataset for 6DoF deformed objects. Most 6D object pose methods assume rigid or articulated objects, an assumption that fails in practice as objects deviate from their canonical shapes due to wear, impact, or deformation. To model this, we introduce the DeSOPE dataset, which features high-fidelity 3D scans of 26 common object categories, each captured in one canonical state and three deformed configurations, with accurate 3D registration to the canonical mesh. Additionally, it features an RGB-D dataset with 133K frames across diverse scenarios and 665K pose annotations produced via a semi-automatic pipeline. We begin by annotating 2D masks for each instance, then compute initial poses using an object pose method, refine them through an object-level SLAM system, and finally perform manual verification to produce the final annotations. We evaluate several object pose methods and find that performance drops sharply with increasing deformation, suggesting that robust handling of such deformations is critical for practical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06720
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Exploring 6D Object Pose Estimation with Deformation
Liu, Zhiqiang
Song, Rui
Chuangqi, Duanmu
Li, Jiaojiao
Ferstl, David
Hu, Yinlin
Computer Vision and Pattern Recognition
We present DeSOPE, a large-scale dataset for 6DoF deformed objects. Most 6D object pose methods assume rigid or articulated objects, an assumption that fails in practice as objects deviate from their canonical shapes due to wear, impact, or deformation. To model this, we introduce the DeSOPE dataset, which features high-fidelity 3D scans of 26 common object categories, each captured in one canonical state and three deformed configurations, with accurate 3D registration to the canonical mesh. Additionally, it features an RGB-D dataset with 133K frames across diverse scenarios and 665K pose annotations produced via a semi-automatic pipeline. We begin by annotating 2D masks for each instance, then compute initial poses using an object pose method, refine them through an object-level SLAM system, and finally perform manual verification to produce the final annotations. We evaluate several object pose methods and find that performance drops sharply with increasing deformation, suggesting that robust handling of such deformations is critical for practical applications.
title Exploring 6D Object Pose Estimation with Deformation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.06720