Liu, MengyaChhatkuli, AjadPostels, JanisGool, Luc VanTombari, FedericoMyszkowski, KarolNiessner, Matthias2023-05-032023-05-0320231467-8659https://doi.org/10.1111/cgf.14745https://diglib.eg.org:443/handle/10.1111/cgf14745Unsupervised template discovery via implicit representation in a category of shapes has recently shown strong performance. At the core, such methods deform input shapes to a common template space which allows establishing correspondences as well as implicit representation of the shapes. In this work we investigate the inherent assumption that the implicit neural field optimization naturally leads to consistently warped shapes, thus providing both good shape reconstruction and correspondences. Contrary to this convenient assumption, in practice we observe that such is not the case, consequently resulting in sub-optimal point correspondences. In order to solve the problem, we re-visit the warp design and more importantly introduce explicit constraints using unsupervised sparse point predictions, directly encouraging consistency of the warped shapes. We use the unsupervised sparse keypoints in order to further condition the deformation warp and enforce the consistency of the deformation warp. Experiments in dynamic non-rigid DFaust and ShapeNet categories show that our problem identification and solution provide the new state-of-the-art in unsupervised dense correspondences.Attribution 4.0 International LicenseCCS Concepts: Modelling -> Shape correspondences; Modeling -> Implicit surface reconstructionModellingShape correspondencesModelingImplicit surface reconstruction10.1111/cgf.1474577-8711 pages