Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Jinyu, Lin, Haitao, Hou, Jiashu, Xue, Xiangyang, Fu, Yanwei
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915551077466112
author Zhang, Jinyu
Lin, Haitao
Hou, Jiashu
Xue, Xiangyang
Fu, Yanwei
author_facet Zhang, Jinyu
Lin, Haitao
Hou, Jiashu
Xue, Xiangyang
Fu, Yanwei
contents Estimating an object's 6D pose, size, and shape from visual input is a fundamental problem in computer vision, with critical applications in robotic grasping and manipulation. Existing methods either rely on object-specific priors such as CAD models or templates, or suffer from limited generalization across categories due to pose-shape entanglement and multi-stage pipelines. In this work, we propose a unified, category-agnostic framework that simultaneously predicts 6D pose, size, and dense shape from a single RGB-D image, without requiring templates, CAD models, or category labels at test time. Our model fuses dense 2D features from vision foundation models with partial 3D point clouds using a Transformer encoder enhanced by a Mixture-of-Experts, and employs parallel decoders for pose-size estimation and shape reconstruction, achieving real-time inference at 28 FPS. Trained solely on synthetic data from 149 categories in the SOPE dataset, our framework is evaluated on four diverse benchmarks SOPE, ROPE, ObjaversePose, and HANDAL, spanning over 300 categories. It achieves state-of-the-art accuracy on seen categories while demonstrating remarkably strong zero-shot generalization to unseen real-world objects, establishing a new standard for open-set 6D understanding in robotics and embodied AI.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View
Zhang, Jinyu
Lin, Haitao
Hou, Jiashu
Xue, Xiangyang
Fu, Yanwei
Computer Vision and Pattern Recognition
Estimating an object's 6D pose, size, and shape from visual input is a fundamental problem in computer vision, with critical applications in robotic grasping and manipulation. Existing methods either rely on object-specific priors such as CAD models or templates, or suffer from limited generalization across categories due to pose-shape entanglement and multi-stage pipelines. In this work, we propose a unified, category-agnostic framework that simultaneously predicts 6D pose, size, and dense shape from a single RGB-D image, without requiring templates, CAD models, or category labels at test time. Our model fuses dense 2D features from vision foundation models with partial 3D point clouds using a Transformer encoder enhanced by a Mixture-of-Experts, and employs parallel decoders for pose-size estimation and shape reconstruction, achieving real-time inference at 28 FPS. Trained solely on synthetic data from 149 categories in the SOPE dataset, our framework is evaluated on four diverse benchmarks SOPE, ROPE, ObjaversePose, and HANDAL, spanning over 300 categories. It achieves state-of-the-art accuracy on seen categories while demonstrating remarkably strong zero-shot generalization to unseen real-world objects, establishing a new standard for open-set 6D understanding in robotics and embodied AI.
title Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.11687