97417 20250612142454.0 doi 10.1007/978-3-030-58595-2_33 sideral 121795 ART-2020-121795 eng Fernandez-Labrador, C. (orcid)0000-0002-3355-6780 Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets 2020 Access copy available to the general public Unrestricted Automatic discovery of category-specific 3D keypoints from a collection of objects of a category is a challenging problem. The difficulty is added when objects are represented by 3D point clouds, with variations in shape and semantic parts and unknown coordinate frames. We define keypoints to be category-specific, if they meaningfully represent objects’ shape and their correspondences can be simply established order-wise across all objects. This paper aims at learning such 3D keypoints, in an unsupervised manner, using a collection of misaligned 3D point clouds of objects from an unknown category. In order to do so, we model shapes defined by the keypoints, within a category, using the symmetric linear basis shapes without assuming the plane of symmetry to be known. The usage of symmetry prior leads us to learn stable keypoints suitable for higher misalignments. To the best of our knowledge, this is the first work on learning such keypoints directly from 3D point clouds for a general category. Using objects from four benchmark datasets, we demonstrate the quality of our learned keypoints by quantitative and qualitative evaluations. Our experiments also show that the keypoints discovered by our method are geometrically and semantically consistent. info:eu-repo/grantAgreement/ES/AEI-FEDER/RTI2018-096903-B-I00 info:eu-repo/grantAgreement/EC/H2020/820434/EU/ENergy aware BIM Cloud Platform in a COst-effective Building REnovation Context/ENCORE This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 820434-ENCORE info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ 0.249 2020 Computer Science (miscellaneous) 2020 Q3 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Chhatkuli, A. Paudel, D.P. Guerrero, J.J. Universidad de Zaragoza (orcid)0000-0001-5209-2267 Demonceaux, C. Gool, L.V. 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. 12370 LNCS (2020), 546-563 Lect. notes comput. sci. Lecture Notes in Computer Science 0302-9743 929386 http://zaguan.unizar.es/record/97417/files/texto_completo.pdf Postprint 251201 http://zaguan.unizar.es/record/97417/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:97417 articulos driver 2025-06-12-14:23:36 ARTICLE