用注意力机制建模手物交互，提升三维姿态重建的物理合理性。
Hand-object reconstruction via interaction-aware graph attention mechanism
- 引入交互感知图注意力，动态连接手与物体节点
- 在真实数据上显著提升手物接触的物理合理性
- 适合做手势识别与人机交互的开发者参考
估计手与物体的位姿已成为视觉计算的重要研究方向，主要挑战在于理解并重建两者间的交互关系，如接触点与物理合理性。现有方法常使用图神经网络融合手与物体网格的空间信息，但未充分挖掘图结构潜力，尤其缺乏对图内及跨图边的动态调整。本文提出一种基于图的优化方法，引入交互感知图注意力机制，通过建立紧密相关节点间的连接，实现手与物体内部及之间的动态关联。实验表明，该方法在物理合理性方面有显著提升。
原文摘要 · Abstract (English)
Estimating the poses of both a hand and an object has become an important area of research due to the growing need for advanced vision computing. The primary challenge involves understanding and reconstructing how hands and objects interact, such as contact and physical plausibility. Existing approaches often adopt a graph neural network to incorporate spatial information of hand and object meshes. However, these approaches have not fully exploited the potential of graphs without modification of edges within and between hand- and object-graphs. We propose a graph-based refinement method that incorporates an interaction-aware graph-attention mechanism to account for hand-object interactions. Using edges, we establish connections among closely correlated nodes, both within individual graphs and across different graphs. Experiments demonstrate the effectiveness of our proposed method with notable improvements in the realm of physical plausibility.
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。