3D Reconstruction of Non-Visible Surfaces of Objects from a Single Depth View – Comparative Study

Uproszczony widok
dc.contributor.authorStaszak, Rafał
dc.contributor.authorMichałek, Piotr
dc.contributor.authorChudziński, Jakub
dc.contributor.authorKopicki, Marek
dc.contributor.authorBelter, Dominik
dc.date.accessioned2023-09-21T06:36:36Z
dc.date.available2023-09-21T06:36:36Z
dc.date.issued2023
dc.description.abstractScene and object reconstruction is an important problem in robotics, in particular in planning collision-free trajectories or in object manipulation. This paper compares two strategies for the reconstruction of nonvisible parts of the object surface from a single RGB-D camera view. The first method, named DeepSDF predicts the Signed Distance Transform to the object surface for a given point in 3D space. The second method, named MirrorNet reconstructs the occluded objects’ parts by generating images from the other side of the observed object. Experiments performed with objects from the ShapeNet dataset, show that the view-dependent MirrorNet is faster and has smaller reconstruction errors in most categories.en_EN
dc.identifier.citationStaszak R., Michałek P., Chudziński J., Kopicki M., Belter D., 3D Reconstruction of Non-Visible Surfaces of Objects from a Single Depth View – Comparative Study. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 19-24, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.1.
dc.identifier.doi10.34658/9788366741928.1
dc.identifier.isbn978-83-66741-92-8
dc.identifier.urihttp://hdl.handle.net/11652/4776
dc.identifier.urihttps://doi.org/10.34658/9788366741928.1
dc.language.isoenen_EN
dc.page.numbers. 19-24
dc.publisherWydawnictwo Politechniki Łódzkiejpl_PL
dc.publisherLodz University of Technology Pressen_EN
dc.relation.ispartofWojciechowski A. (Ed.), Lipiński P. (Ed.)., Progress in Polish Artificial Intelligence Research 4, Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.
dc.rightsDla wszystkich w zakresie dozwolonego użytkupl_PL
dc.rightsFair use conditionen_EN
dc.rights.licenseLicencja PŁpl_PL
dc.rights.licenseLUT Licenseen_EN
dc.subjectroboticsen_EN
dc.subjectscene reconstructionen_EN
dc.subjectneural scene representationen_EN
dc.subjectrobotykaen_EN
dc.subjectrekonstrukcja scenpl_PL
dc.subjectreprezentacja scen neuronowychpl_PL
dc.title3D Reconstruction of Non-Visible Surfaces of Objects from a Single Depth View – Comparative Studyen_EN
dc.typeRozdział - monografiapl_PL
dc.typeChapter - monographen_EN

Pliki

Oryginalne pliki
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
1. 3D_Reconstr_Staszak_Michalek_2023.pdf
Rozmiar:
1.96 MB
Format:
Adobe Portable Document Format
Opis:
Pobierz
Licencja
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
license.txt
Rozmiar:
1.71 KB
Format:
Item-specific license agreed upon to submission
Opis:
Pobierz

Kolekcje

Rozdziały