通过几何点注意力机制提升3D零件重组的精度与一致性
Geometric Point Attention Transformer for 3D Shape Reassembly
- 引入几何点注意力模块，融合全局形状与局部几何特征
- 迭代更新机制使姿态预测准确率显著提升，对齐误差更低
- 适合需要高精度3D重建与零件装配的工业设计场景
形状组装旨在将分离的部件重新组合成完整物体，近年来受到广泛关注。现有方法主要依赖网络预测各部件的姿态，但难以有效捕捉部件间的几何相互作用及其姿态关系。本文提出几何点注意力变压器（GPAT），专门解决几何关系推理难题。在几何点注意力模块中，整合全局形状信息、局部成对几何特征以及每个部件的旋转和平移向量表示。为实现迭代更新与动态推理，引入几何回流机制，将每次预测结果反馈至下一轮进行优化。在语义与几何组装任务上评估模型，结果表明其在绝对姿态估计上优于先前方法，实现了更精准的姿态预测和更高的对齐精度。
原文摘要 · Abstract (English)
Shape assembly, which aims to reassemble separate parts into a complete object, has gained significant interest in recent years. Existing methods primarily rely on networks to predict the poses of individual parts, but often fail to effectively capture the geometric interactions between the parts and their poses. In this paper, we present the Geometric Point Attention Transformer (GPAT), a network specifically designed to address the challenges of reasoning about geometric relationships. In the geometric point attention module, we integrate both global shape information and local pairwise geometric features, along with poses represented as rotation and translation vectors for each part. To enable iterative updates and dynamic reasoning, we introduce a geometric recycling scheme, where each prediction is fed into the next iteration for refinement. We evaluate our model on both the semantic and geometric assembly tasks, showing that it outperforms previous methods in absolute pose estimation, achieving accurate pose predictions and high alignment accuracy.
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。