A new fringe analysis method based on shared bottom network for single frame 3D reconstruction

Jin Lu; Min Jie Zhang; Mu H. Li; Mu J. Li; Jin Wang; Pei Y. Wu; Wei Sun; Lin Li

doi:10.1117/12.3048685

5 December 2024 A new fringe analysis method based on shared bottom network for single frame 3D reconstruction

Jin Lu, Min Jie Zhang, Mu H. Li, Mu J. Li, Jin Wang, Pei Y. Wu, Wei Sun, Lin Li

Proceedings Volume 13418, Fifteenth International Conference on Information Optics and Photonics (CIOP 2024); 1341838 (2024) https://doi.org/10.1117/12.3048685
Event: 15th International Conference on Information Optics and Photonics (CIOP2024), 2024, Xi’an, China

Abstract

Recently, deep learning-based methods have been employed in optical measurement. The fringe to phase method based on deep learning can achieve high-precision 3D topography measurement and is applied to various optical metrology tasks, including phase extraction, phase unwrapping, fringe order determination, depth estimation, and other crucial steps. However, it appears simplistic to obtain images of each metrological task from a single fringe pattern. This paper proposes a novel network that effectively extracts the semantic features of fringe patterns by incorporating the design architecture of transformer while retaining the advantages of convolutional networks. The architecture primarily consists of a backbone, decoder, and feature extraction block which enhance the features at different frequencies within a single fringe pattern. The backbone and decoder are specifically designed for wrapped phase prediction tasks. Experimental results demonstrate that the network accurately predicts the wrapped phase from a single fringe pattern. In comparison with previous methods, this paper's approach offers several contributions: an efficient utilization of a new type of encoder for extracting high-level semantic features from fringe patterns; moreover, only a single grayscale image is required as input for the network without relying on color composite images or additional prior information.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jin Lu, Min Jie Zhang, Mu H. Li, Mu J. Li, Jin Wang, Pei Y. Wu, Wei Sun, and Lin Li "A new fringe analysis method based on shared bottom network for single frame 3D reconstruction", Proc. SPIE 13418, Fifteenth International Conference on Information Optics and Photonics (CIOP 2024), 1341838 (5 December 2024); https://doi.org/10.1117/12.3048685

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Fringe analysis

Feature extraction

Convolution

Semantics

Network architectures

Phase unwrapping

3D modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years