Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections
This addresses the limitation of ignoring 3D geometry in graph matching for computer vision, offering improved performance for object category analysis.
The paper tackles the problem of graph matching in 2D images by jointly learning correspondences and 3D geometry, outperforming recent methods in accuracy and cycle-consistency error.
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.