Share Email Print

Proceedings Paper

Deep photometric learning (DPL)
Author(s): Tanaporn Na Narong; Denis Sharoukhov; Tonislav Ivanov; Vadim Pinskiy; Matthew Putman
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Photometric stereo is a common technique for 3D reconstruction by calculating the surface normals of an object from different illumination angles. The technique is effective to estimate height profile of static objects with large features, but often fails for objects with smaller features or in flat environments with small depressions. We propose a method using deep learning to perform 3D reconstruction of small features. Our method handles sample noise, uneven illumination, and surface tilt. We demonstrate decreased noise susceptibility on synthetic data and promising performance on experimental datasets. This approach enables rapid inspection and reconstruction of complex surfaces without the need to use destructive or expensive analysis methods.

Paper Details

Date Published: 5 March 2020
PDF: 14 pages
Proc. SPIE 11281, Oxide-based Materials and Devices XI, 1128110 (5 March 2020); doi: 10.1117/12.2555925
Show Author Affiliations
Tanaporn Na Narong, Stanford Univ. (United States)
Nanotronics (United States)
Denis Sharoukhov, Nanotronics (United States)
Tonislav Ivanov, Nanotronics (United States)
Vadim Pinskiy, Nanotronics (United States)
Matthew Putman, Nanotronics (United States)

Published in SPIE Proceedings Vol. 11281:
Oxide-based Materials and Devices XI
David J. Rogers; David C. Look; Ferechteh H. Teherani, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?