Multi-scale and attention training of uncalibrated photometric stereo networks

Tianhang Zheng; Lili Cao; Yongjian Zhu

doi:10.1117/12.3026439

27 March 2024 Multi-scale and attention training of uncalibrated photometric stereo networks

Tianhang Zheng, Lili Cao, Yongjian Zhu

Proceedings Volume 13105, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023); 1310516 (2024) https://doi.org/10.1117/12.3026439
Event: 3rd International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023), 2023, Qingdao, China

Abstract

In this paper, an uncalibrated photometric stereo network model is proposed. Traditional photometric stereo has precise requirements on light source and object surface reflectance, which greatly limits the usability of photometric stereo, and the ideal network model should be able to handle arbitrary objects under uncalibrated light sources to complete the reconstruction. To solve this problem, we propose an uncalibrated photometric stereo neural network, First, an arbitrary number of images are input to the first-stage neural network system to estimate the light source information and complete the calibration to eliminate the dependence on the light source information. Then the calibration result is input to the second-stage neural network together with the image, and the multi-scale and attention mechanism is used to obtain the object surface texture information to achieve the surface normal reconstruction of the object. Our network (MAPS-Net) is compared with other uncalibrated photometric stereo methods on the DiLiGenT benchmark, and the average MAE achieves an excellent performance of 9.20.

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

Citation Download Citation

Tianhang Zheng, Lili Cao, and Yongjian Zhu "Multi-scale and attention training of uncalibrated photometric stereo networks", Proc. SPIE 13105, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023), 1310516 (27 March 2024); https://doi.org/10.1117/12.3026439

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
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Light sources

Education and training

Data modeling

Feature extraction

Light sources and illumination

Image restoration

Performance modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years