KASALv2：全自动 3D 旋转对称分类与轴定位
KASALv2: Fully Automatic 3D Rotational Symmetry Classification and Axis Localization
提出全自动、无参考的 3D 旋转对称类型分类与轴定位框架，可直接作为 6D 位姿估计的对称性先验，替代人工标注，提升 FoundationPose 在 BOP 数据集上的精度。
原文依据 Training FoundationPose with these priors improves accuracy by up to 0.9% across five BOP datasets
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论旋转对称性是 6D 位姿估计中的重要先验，可提高位姿精度并支持对称性感知的评估。然而，当前 3D 物体的对称性标注仍主要依赖人工或半自动方式，通常需要预定义类型或阶数，限制了可扩展性。本文提出一个全自动、无参考的框架，用于在全部八种典型 3D 旋转对称类型上进行对称类型分类、旋转阶数识别和完整轴定位。该方法定位主导的高阶轴，通过自一致性分析推断其旋转阶数，并在层次引导的公式下重建完整的对称结构。纹理感知扩展进一步建模外观引起的旋转阶数降低，同时保持轴方向。在理想化和真实世界数据集上的实验证明了较强的准确性和泛化能力，在 GSO 的 438 个对称物体上达到 94.75% 的准确率。使用这些先验训练 FoundationPose 在五个 BOP 数据集上精度提升高达 0.9%，表明自动估计的旋转先验可改善下游 6D 位姿估计。代码见 https://github.com/WangYuLin-SEU/KASAL。
英文原文摘要 1247 字符
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.