联合深度多图匹配和来自非均匀2D图像集合的3D几何学习
Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections
摘要：
图匹配的目的是在图的顶点之间建立对应关系，使得节点和边属性都一致。最近提出了各种基于学习的方法，用于基于深度图匹配公式找到图像关键点之间的对应关系。虽然这些方法主要集中在学习节点和边缘属性，但它们完全忽略了2D图像中描绘的底层3D对象的3D几何形状。我们通过提出一个可训练的框架来填补这一空白，该框架利用图神经网络从非均匀图像集合中学习可变形的3D几何模型，即，一组图像，描绘来自同一类别的对象的不同实例。在实验中，我们证明了我们的方法优于最近的基于学习的方法，考虑到准确性和周期一致性误差的图匹配，同时我们还获得了2D图像中描绘的对象的底层3D几何形状。
英文摘要：
Graph matching aims to establish correspondences between vertices of graphs such that both the node and edge attributes agree. Various learning-based methods were recently proposed for finding correspondences between image key points based on deep graph matching formulations. While these approaches mainly focus on learning node and edge attributes, they completely ignore the 3D geometry of the underlying 3D objects depicted in the 2D images. We fill this gap by proposing a trainable framework that takes advantage of graph neural networks for learning a deformable 3D geometry model from inhomogeneous image collections, i.e.,~a set of images that depict different instances of objects from the same category. Experimentally, we demonstrate that our method outperforms recent learning-based approaches for graph matching considering both accuracy and cycle-consistency error, while we in addition obtain the underlying 3D geometry of the objects depicted in the 2D images.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
