Deep Tracking for Robust Real-time Object Scanning

No Thumbnail Available
Date
2022
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Nowadays, a high-fidelity 3d model representation can be obtained easily by means of handheld optical scanners, which offer a good level of reconstruction quality, portability, and low latency in scan-to-data. However, it is well known that the tracking process can be critical for such devices: sub-optimal lighting conditions, smooth surfaces in the scene, or occluded views and repetitive patterns are all sources of error. In this scenario, recent disruptive technologies such as sparse convolutional neural networks have been tailored to address common problems in 3D vision and analysis. Our work aims to integrate the most promising solutions into an operating framework which can then be used to achieve compelling results in 3D real-time reconstruction. Several scenes from a dataset containing dense views of objects are tested using our proposed pipeline and compared with the current state-of-the-art of online reconstruction.
Description

CCS Concepts: Computing methodologies -> Reconstruction; 3D imaging; Tracking; Artificial intelligence; Hardware -> Emerging tools and methodologies

        
@inproceedings{
10.2312:stag.20221262
, booktitle = {
Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference
}, editor = {
Cabiddu, Daniela
and
Schneider, Teseo
and
Allegra, Dario
and
Catalano, Chiara Eva
and
Cherchi, Gianmarco
and
Scateni, Riccardo
}, title = {{
Deep Tracking for Robust Real-time Object Scanning
}}, author = {
Lombardi, Marco
and
Savardi, Mattia
and
Signoroni, Alberto
}, year = {
2022
}, publisher = {
The Eurographics Association
}, ISSN = {
2617-4855
}, ISBN = {
978-3-03868-191-5
}, DOI = {
10.2312/stag.20221262
} }
Citation