无需训练，用视觉模型检测3D对称面，效果超越传统与学习方法。
Training-free zero-shot 3D symmetry detection with visual features back-projected to geometry
- 从渲染视图提取视觉特征，回投影到3D几何体上
- 在ShapeNet子集上达到优于几何与学习方法的对称检测精度
- 首次展示基础视觉模型解决复杂3D几何问题的能力
我们提出一种简单有效的无训练零样本3D对称性检测方法，利用DINOv2等基础视觉模型的视觉特征。该方法从3D物体的渲染视图中提取特征，并将其回投影至原始几何结构上。实验表明这些特征具有对称不变性，可通过所提算法识别反射对称平面。在ShapeNet子集上的测试显示，该方法优于传统几何方法和基于学习的方法，且无需任何训练数据。本工作展示了基础视觉模型在解决复杂3D几何问题（如对称性检测）中的潜力。
原文摘要 · Abstract (English)
We present a simple yet effective training-free approach for zero-shot 3D symmetry detection that leverages visual features from foundation vision models such as DINOv2. Our method extracts features from rendered views of 3D objects and backprojects them onto the original geometry. We demonstrate the symmetric invariance of these features and use them to identify reflection-symmetry planes through a proposed algorithm. Experiments on a subset of ShapeNet demonstrate that our approach outperforms both traditional geometric methods and learning-based approaches without requiring any training data. Our work demonstrates how foundation vision models can help in solving complex 3D geometric problems such as symmetry detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。