Deep Learning Methods for Calibrated Photometric Stereo and Beyond
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-11 · 46 (11) · 7154-7172
DOI: 10.1109/tpami.2024.3388150 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-11. Verfasst von Yakun Ju und 5 weiteren Autor:innen. Die Arbeit wurde bisher 66-mal zitiert (Crossref) und nennt 105 Literaturangaben. Gefördert von: National Key R&D Program of China, National Key Scientific Instrument and Equipment Development Projects of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Photometric stereo recovers the surface normals of an object from multiple images with varying shading cues, i.e., modeling the relationship between surface orientation and intensity at each pixel. Photometric stereo prevails in superior per-pixel resolution and fine reconstruction details. However, it is a complicated problem because of the non-linear relationship caused by non-Lambertian surface reflectance. Recently, various deep learning methods have shown a powerful ability in the context of photometric stereo against non-Lambertian surfaces. This paper provides a comprehensive review of existing deep learning-based calibrated photometric stereo methods utilizing orthographic cameras and directional light sources. We first analyze these methods from different perspectives, including input processing, supervision, and network architecture. We summarize the performance of deep learning photometric stereo models on the most widely-used benchmark data set. This demonstrates the advanced performance of deep learning-based photometric stereo methods. Finally, we give suggestions and propose future research trends based on the limitations of existing models.
Förderung
- National Key R&D Program of China
- National Key Scientific Instrument and Equipment Development Projects of China
- National Natural Science Foundation of China
- Project of Strategic Importance Fund from The Hong Kong Polytechnic University
Zitieren
APA
Ju, Y., Lam, K. M., Xie, W., Zhou, H., Dong, J., & Shi, B. (2024). Deep Learning Methods for Calibrated Photometric Stereo and Beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(11), 7154-7172. https://doi.org/10.1109/tpami.2024.3388150
Vancouver
Ju Y, Lam KM, Xie W, Zhou H, Dong J, Shi B. Deep Learning Methods for Calibrated Photometric Stereo and Beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(11):7154-7172. doi:10.1109/tpami.2024.3388150
BibTeX
@article{Ju2024,
author = {Ju, Yakun and Lam, Kin-Man and Xie, Wuyuan and Zhou, Huiyu and Dong, Junyu and Shi, Boxin},
title = {Deep Learning Methods for Calibrated Photometric Stereo and Beyond},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {11},
pages = {7154--7172},
doi = {10.1109/tpami.2024.3388150}
}
EUVIMED