Single Shot Phase Shift 3D Scanning with Convolutional Neural Network and Synthetic Fractals

Simple item page
dc.contributor.authorLi, Keen_US
dc.contributor.authorSpehr, Marcelen_US
dc.contributor.authorHöhne, Danielen_US
dc.contributor.authorBräuer-Burchardt, Christianen_US
dc.contributor.authorTünnermann, Andreasen_US
dc.contributor.authorKühmstedt, Peteren_US
dc.contributor.editorBerretti, Stefanoen_US
dc.contributor.editorThehoaris, Theoharisen_US
dc.contributor.editorDaoudi, Mohameden_US
dc.contributor.editorFerrari, Claudioen_US
dc.contributor.editorVeltkamp, Remco C.en_US
dc.date.accessioned2022-08-31T07:10:19Z
dc.date.available2022-08-31T07:10:19Z
dc.date.issued2022
dc.description.abstractThe phase shift algorithm is an important 3D shape reconstruction method in industrial quality inspection and reverse engineering. To retrieve dense and accurate point clouds, the conventional phase shift methods require at least three fringe projection patterns, limiting its application to statics or semi-statics scenes only. In this paper, we propose a novel and low-cost single-shot phase shift 3D reconstruction framework using convolution neural networks (CNN) trained on 3D synthetic fractals. We first design and optimize a novel projection pattern that compresses the phase period orders and the ambiguous phase information into a single image. Then, we train two different CNNs to predict the ambiguous phase information and the period orders separately. The CNNs were trained on randomly generated 3D shapes whose geometric complexity is modeled by recursive shape generation algorithms which can create an unlimited amount of random 3D shapes on the fly. Initial results demonstrate that our method can produce high-quality point clouds from just a pair of 2D images, thus improving the temporal resolution of a phase-shift 3D scanner to the highest possible. As we also include different real-world lighting and textural conditions in the training data set, experiments also demonstrate that our CNN models which were trained on random synthetic fractals only can perform equally well in the real world.en_US
dc.description.sectionheadersShort Papers
dc.description.seriesinformationEurographics Workshop on 3D Object Retrieval
dc.identifier.doi10.2312/3dor.20221179
dc.identifier.isbn978-3-03868-174-8
dc.identifier.issn1997-0471
dc.identifier.pages9-16
dc.identifier.pages8 pages
dc.identifier.urihttps://doi.org/10.2312/3dor.20221179
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/3dor20221179
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → 3D imaging; Neural networks; Modeling methodologies
dc.subjectComputing methodologies → 3D imaging
dc.subjectNeural networks
dc.subjectModeling methodologies
dc.titleSingle Shot Phase Shift 3D Scanning with Convolutional Neural Network and Synthetic Fractalsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
009-016.pdf
Size:
1.71 MB
Format:
Adobe Portable Document Format
Download
Collections
3DOR 2022 - Short Papers