000097417 001__ 97417
000097417 005__ 20210902121842.0
000097417 0247_ $$2doi$$a10.1007/978-3-030-58595-2_33
000097417 0248_ $$2sideral$$a121795
000097417 037__ $$aART-2020-121795
000097417 041__ $$aeng
000097417 100__ $$0(orcid)0000-0002-3355-6780$$aFernandez-Labrador, C.
000097417 245__ $$aUnsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets
000097417 260__ $$c2020
000097417 5060_ $$aAccess copy available to the general public$$fUnrestricted
000097417 5203_ $$aAutomatic discovery of category-specific 3D keypoints from a collection of objects of a category is a challenging problem. The difficulty is added when objects are represented by 3D point clouds, with variations in shape and semantic parts and unknown coordinate frames. We define keypoints to be category-specific, if they meaningfully represent objects’ shape and their correspondences can be simply established order-wise across all objects. This paper aims at learning such 3D keypoints, in an unsupervised manner, using a collection of misaligned 3D point clouds of objects from an unknown category. In order to do so, we model shapes defined by the keypoints, within a category, using the symmetric linear basis shapes without assuming the plane of symmetry to be known. The usage of symmetry prior leads us to learn stable keypoints suitable for higher misalignments. To the best of our knowledge, this is the first work on learning such keypoints directly from 3D point clouds for a general category. Using objects from four benchmark datasets, we demonstrate the quality of our learned keypoints by quantitative and qualitative evaluations. Our experiments also show that the keypoints discovered by our method are geometrically and semantically consistent.
000097417 536__ $$9info:eu-repo/grantAgreement/ES/AEI-FEDER/RTI2018-096903-B-I00$$9info:eu-repo/grantAgreement/EC/H2020/820434/EU/ENergy aware BIM Cloud Platform in a COst-effective Building REnovation Context/ENCORE$$9This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 820434-ENCORE
000097417 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000097417 592__ $$a0.249$$b2020
000097417 593__ $$aComputer Science (miscellaneous)$$c2020$$dQ3
000097417 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000097417 700__ $$aChhatkuli, A.
000097417 700__ $$aPaudel, D.P.
000097417 700__ $$0(orcid)0000-0001-5209-2267$$aGuerrero, J.J.$$uUniversidad de Zaragoza
000097417 700__ $$aDemonceaux, C.
000097417 700__ $$aGool, L.V.
000097417 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát.
000097417 773__ $$g12370 LNCS (2020), 546-563$$pLect. notes comput. sci.$$tLecture Notes in Computer Science$$x0302-9743
000097417 8564_ $$s929386$$uhttps://zaguan.unizar.es/record/97417/files/texto_completo.pdf$$yPostprint
000097417 8564_ $$s251201$$uhttps://zaguan.unizar.es/record/97417/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000097417 909CO $$ooai:zaguan.unizar.es:97417$$particulos$$pdriver
000097417 951__ $$a2021-09-02-10:24:34
000097417 980__ $$aARTICLE