A novel surface normal estimation method using smooth L1 regression for photometric stereo

Wenjie Li; Long Ma; Xu Liu; Xutao Yin; Xin Pei; Xinyi Zhao

doi:10.1117/12.3035846

20 November 2024 A novel surface normal estimation method using smooth L1 regression for photometric stereo

Wenjie Li, Long Ma, Xu Liu, Xutao Yin, Xin Pei, Xinyi Zhao

Author Affiliations +

Proceedings Volume 13241, Optical Metrology and Inspection for Industrial Applications XI; 132410S (2024) https://doi.org/10.1117/12.3035846
Event: SPIE/COS Photonics Asia, 2024, Nantong, Jiangsu, China

Abstract

Photometric stereo reconstructs surface shape with intricate details by analyzing the light propagation process and has attracted wide range of applications such as industrial measurement. However, the presence of non-Lambertian reflections on real-world scenarios poses a significant challenge to surface normal estimation methods. Most of the existing approaches aim to achieve reasonably accurate results by filtering non-Lambertian observations through employing iterative frameworks. Based on these, this study introduces a novel surface normal estimation method that formulates the observation selection and regularization as a smooth L₁ regression problem. Specifically, we sort pixels by intensities and select effective observations through a threshold strategy, the surface normal are then estimated by a smooth L₁ loss function to resist non-Lambertian corrosions so that facilitate a more accurate result. The performance of the method is validated through testing on real-world datasets, with an impressive average angular error as low as 11.92°. In experiments, surface reconstruction of a turbine blade is successfully achieved, showcasing its applicability in industrial manufacturing.

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

Citation Download Citation

Wenjie Li, Long Ma, Xu Liu, Xutao Yin, Xin Pei, and Xinyi Zhao "A novel surface normal estimation method using smooth L1 regression for photometric stereo", Proc. SPIE 13241, Optical Metrology and Inspection for Industrial Applications XI, 132410S (20 November 2024); https://doi.org/10.1117/12.3035846

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