3D Reconstruction of Non-Visible Surfaces of Objects from a Single Depth View – Comparative Study
Data
2023
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
Lodz University of Technology Press
Abstrakt
Scene 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.
Opis
Słowa kluczowe
robotics, scene reconstruction, neural scene representation, robotyka, rekonstrukcja scen, reprezentacja scen neuronowych
Cytowanie
Staszak 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.