aiqbench analysis
This research presents a fully automatic framework for classifying 3D rotational symmetry types and localizing their axes, addressing scalability issues in current manual annotation methods. By integrating these automatically estimated priors into FoundationPose models, the study achieves measurable improvements in downstream 6D pose estimation accuracy across multiple datasets. The work advances computer vision capabilities by enabling robust, reference-free symmetry analysis essential for complex robotic manipulation and scene understanding tasks.
KASALv2: Fully Automatic 3D Rotational Symmetry Classification and Axis Localization
arXiv:2610.09534v1 Announce Type: cross Abstract: Rotational symmetry is an important prior in 6D pose estimation, improving pose accuracy and supporting symmetry-aware evaluation. However, current symmetry annotations for 3D objects remain largely manual or semi-automatic, often requiring predefined types or orders, which limits scalability. This work introduces a fully automatic, reference-free framework for symmetry-type classification, rotational-order identification, and full-axis localization across all eight canonical 3D rotational symmetry types. The method localizes a dominant high-order axis, infers its rotational order through self-consistency analysis, and reconstructs the complete symmetry structure under a hierarchy-guided formulation. A texture-aware extension further models appearance-induced reductions in rotational order while preserving axis orientations. Experiments on idealized and real-world datasets demonstrate strong accuracy and generalization, achieving 94.75% accuracy on 438 symmetric objects in GSO. Training FoundationPose with these priors improves accuracy by up to 0.9% across five BOP datasets, showing that automatically estimated rotational priors improve downstream 6D pose estimation. Code is available at https://github.com/WangYuLin-SEU/KASAL.
Abstract:Rotational symmetry is an important prior in 6D pose estimation, improving pose accuracy and supporting symmetry-aware evaluation. However, current symmetry annotations for 3D objects remain largely manual or semi-automatic, often requiring predefined types or orders, which limits scalability. This work introduces a fully automatic, reference-free framework for symmetry-type classification, rotational-order identification, and full-axis localization across all eight canonical 3D rotational symmetry types. The method localizes a dominant high-order axis, infers its rotational order through self-consistency analysis, and reconstructs the complete symmetry structure under a hierarchy-guided formulation. A texture-aware extension further models appearance-induced reductions in rotational order while preserving axis orientations. Experiments on idealized and real-world datasets demonstrate strong accuracy and generalization, achieving 94.75% accuracy on 438 symmetric objects in GSO. Training FoundationPose with these priors improves accuracy by up to 0.9% across five BOP datasets, showing that automatically estimated rotational priors improve downstream 6D pose estimation. Code is available at this https URL.
CVPR 2026. 10 pages, 4 figures. Mengxin Zhang and Yulin Wang contributed equally. Corresponding authors: Chen Luo and Yijun Zhou
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Graphics (cs.GR)
arXiv:2610.09534 [cs.CV]
(or arXiv:2610.09534v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.09534 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 13866-13875
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 290 words
Related coverage
Utrecht University Cuts Simulation Times with New Symmetry Tool
Quantum Zeitgeist · Sep 10, 2026
The Entangled Dimensions of Decision Theory
LessWrong · Jul 30, 2026
Macao Polytechnic Team Detects Angular Order in Complex Images
Quantum Zeitgeist · Aug 19, 2026
Imaging the topological sign of a Dirac mass with spin-polarized tunneling
arXiv · Oct 14, 2026