Li, KeSpehr, MarcelHöhne, DanielBräuer-Burchardt, ChristianTünnermann, AndreasKühmstedt, PeterBerretti, StefanoThehoaris, TheoharisDaoudi, MohamedFerrari, ClaudioVeltkamp, Remco C.2022-08-312022-08-312022978-3-03868-174-81997-0471https://doi.org/10.2312/3dor.20221179https://diglib.eg.org:443/handle/10.2312/3dor20221179The 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.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → 3D imaging; Neural networks; Modeling methodologiesComputing methodologies → 3D imagingNeural networksModeling methodologies10.2312/3dor.202211799-168 pages