From Single Shot to Structure: End-to-End Network-Based Deflectometry for Specular Free-Form Surface Reconstruction

Sepanj, M.Hadi; Moradi, Saed; Nazemi, Amir; Preston, Claire; Lee, Anthony M. D.; Fieguth, Paul

doi:10.3390/app142310824

Open AccessArticle

From Single Shot to Structure: End-to-End Network-Based Deflectometry for Specular Free-Form Surface Reconstruction

by

M.Hadi Sepanj

¹

,

Saed Moradi

¹

,

Amir Nazemi

¹

,

Claire Preston

²

,

Anthony M. D. Lee

²

and

Paul Fieguth

^1,*

¹

Vision and Image Processing Laboratory, Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada

²

General Fusion Inc., 6020 Russ Baker Way, Richmond, BC V7B 1B4, Canada

^*

Author to whom correspondence should be addressed.

Appl. Sci. 2024, 14(23), 10824; https://doi.org/10.3390/app142310824

Submission received: 19 September 2024 / Revised: 1 November 2024 / Accepted: 14 November 2024 / Published: 22 November 2024

(This article belongs to the Special Issue Technical Advances in 3D Reconstruction)

Download

Browse Figures

Versions Notes

Abstract

Deflectometry is a key component in the precise measurement of specular (mirrored) surfaces; however, traditional methods often lack an end-to-end approach that performs 3D reconstruction in a single shot with high accuracy and generalizes across different free-form surfaces. This paper introduces a novel deep neural network (DNN)-based approach for end-to-end 3D reconstruction of free-form specular surfaces using single-shot deflectometry. Our proposed network, VUDNet, innovatively combines discriminative and generative components to accurately interpret orthogonal fringe patterns and generate high-fidelity 3D surface reconstructions. By leveraging a hybrid architecture integrating a Variational Autoencoder (VAE) and a modified U-Net, VUDNet excels in both depth estimation and detail refinement, achieving superior performance in challenging environments. Extensive data simulation using Blender leading to a dataset which we will make available, ensures robust training and enables the network to generalize across diverse scenarios. Experimental results demonstrate the strong performance of VUDNet, setting a new standard for 3D surface reconstruction.

Keywords: deflectometry; specular surface reconstruction; deep neural networks; single-shot measurement; data simulation; variational autoencoder (VAE)

Share and Cite

MDPI and ACS Style

Sepanj, M.H.; Moradi, S.; Nazemi, A.; Preston, C.; Lee, A.M.D.; Fieguth, P. From Single Shot to Structure: End-to-End Network-Based Deflectometry for Specular Free-Form Surface Reconstruction. Appl. Sci. 2024, 14, 10824. https://doi.org/10.3390/app142310824

AMA Style

Sepanj MH, Moradi S, Nazemi A, Preston C, Lee AMD, Fieguth P. From Single Shot to Structure: End-to-End Network-Based Deflectometry for Specular Free-Form Surface Reconstruction. Applied Sciences. 2024; 14(23):10824. https://doi.org/10.3390/app142310824

Chicago/Turabian Style

Sepanj, M.Hadi, Saed Moradi, Amir Nazemi, Claire Preston, Anthony M. D. Lee, and Paul Fieguth. 2024. "From Single Shot to Structure: End-to-End Network-Based Deflectometry for Specular Free-Form Surface Reconstruction" Applied Sciences 14, no. 23: 10824. https://doi.org/10.3390/app142310824

APA Style

Sepanj, M. H., Moradi, S., Nazemi, A., Preston, C., Lee, A. M. D., & Fieguth, P. (2024). From Single Shot to Structure: End-to-End Network-Based Deflectometry for Specular Free-Form Surface Reconstruction. Applied Sciences, 14(23), 10824. https://doi.org/10.3390/app142310824

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

From Single Shot to Structure: End-to-End Network-Based Deflectometry for Specular Free-Form Surface Reconstruction

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI