用3D几何先验提升2D旋转对称检测的准确性
Leveraging 3D Geometric Priors in 2D Rotation Symmetry Detection
- 在3D空间预测对称中心和顶点，再投影回2D保持结构一致
- 在DENDI数据集上对称轴检测准确率显著提升
- 适合需要高精度对称性识别的计算机视觉任务
对称性在理解结构模式、辅助物体识别与场景解析中至关重要。本文聚焦于旋转对称性，即物体绕中心轴旋转后保持不变，需检测旋转中心与支撑顶点。传统方法依赖手工特征匹配，而基于卷积神经网络的分割模型虽能检测旋转中心，但在视角扭曲下难以保证3D几何一致性。为此，我们提出一种直接在3D空间预测旋转中心与顶点，并将其投影回2D的方法，同时通过顶点重建阶段施加3D几何先验（如边长相等、内角一致）以增强鲁棒性与准确性。在DENDI数据集上的实验表明，该方法在旋转轴检测上表现更优，消融实验证明了3D先验的有效性。
原文摘要 · Abstract (English)
Symmetry plays a vital role in understanding structural patterns, aiding object recognition and scene interpretation. This paper focuses on rotation symmetry, where objects remain unchanged when rotated around a central axis, requiring detection of rotation centers and supporting vertices. Traditional methods relied on hand-crafted feature matching, while recent segmentation models based on convolutional neural networks detect rotation centers but struggle with 3D geometric consistency due to viewpoint distortions. To overcome this, we propose a model that directly predicts rotation centers and vertices in 3D space and projects the results back to 2D while preserving structural integrity. By incorporating a vertex reconstruction stage enforcing 3D geometric priors -- such as equal side lengths and interior angles -- our model enhances robustness and accuracy. Experiments on the DENDI dataset show superior performance in rotation axis detection and validate the impact of 3D priors through ablation studies.
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。