Next Article in Journal
On the Impact of Biceps Muscle Fatigue in Human Activity Recognition
Next Article in Special Issue
HRDepthNet: Depth Image-Based Marker-Less Tracking of Body Joints
Previous Article in Journal
Reinforcement Learning-Based Complete Area Coverage Path Planning for a Modified hTrihex Robot
Previous Article in Special Issue
A Systematic Comparison of Depth Map Representations for Face Recognition
Article

Surface Reconstruction from Structured Light Images Using Differentiable Rendering

1
DTU Compute, Technical University of Denmark, 2800 Kgs. Lyngby, Denmark
2
SDU Robotics, University of Southern Denmark, 5230 Odense, Denmark
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editors: Matteo Poggi and Thomas Moeslund
Sensors 2021, 21(4), 1068; https://doi.org/10.3390/s21041068
Received: 21 December 2020 / Revised: 29 January 2021 / Accepted: 31 January 2021 / Published: 4 February 2021
(This article belongs to the Special Issue Computer Vision for 3D Perception and Applications)
When 3D scanning objects, the objective is usually to obtain a continuous surface. However, most surface scanning methods, such as structured light scanning, yield a point cloud. Obtaining a continuous surface from a point cloud requires a subsequent surface reconstruction step, which is directly affected by any error from the computation of the point cloud. In this work, we propose a one-step approach in which we compute the surface directly from structured light images. Our method minimizes the least-squares error between photographs and renderings of a triangle mesh, where the vertex positions of the mesh are the parameters of the minimization problem. To ensure fast iterations during optimization, we use differentiable rendering, which computes images and gradients in a single pass. We present simulation experiments demonstrating that our method for computing a triangle mesh has several advantages over approaches that rely on an intermediate point cloud. Our method can produce accurate reconstructions when initializing the optimization from a sphere. We also show that our method is good at reconstructing sharp edges and that it is robust with respect to image noise. In addition, our method can improve the output from other reconstruction algorithms if we use these for initialization. View Full-Text
Keywords: 3D surface reconstruction; 3D scanning; structured light; differentiable rendering 3D surface reconstruction; 3D scanning; structured light; differentiable rendering
Show Figures

Figure 1

MDPI and ACS Style

Jensen, J.N.; Hannemose, M.; Bærentzen, J.A.; Wilm, J.; Frisvad, J.R.; Dahl, A.B. Surface Reconstruction from Structured Light Images Using Differentiable Rendering. Sensors 2021, 21, 1068. https://doi.org/10.3390/s21041068

AMA Style

Jensen JN, Hannemose M, Bærentzen JA, Wilm J, Frisvad JR, Dahl AB. Surface Reconstruction from Structured Light Images Using Differentiable Rendering. Sensors. 2021; 21(4):1068. https://doi.org/10.3390/s21041068

Chicago/Turabian Style

Jensen, Janus N., Morten Hannemose, J. A. Bærentzen, Jakob Wilm, Jeppe R. Frisvad, and Anders B. Dahl. 2021. "Surface Reconstruction from Structured Light Images Using Differentiable Rendering" Sensors 21, no. 4: 1068. https://doi.org/10.3390/s21041068

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop