Data-driven polarimetric approaches fuel computational imaging expansion

Incorporating polarization in computer vision tasks provides new solutions to high-level analytics, in particular when coupled with machine learning frameworks such as convolutional neural networks (CNN). A recent review in Opto-Electronic Science reports on the developments in data-driven polarimet...

Full description

Saved in:
Bibliographic Details
Main Author: Sylvain Gigan
Format: Article
Language:English
Published: Institue of Optics and Electronics, Chinese Academy of Sciences 2024-09-01
Series:Opto-Electronic Advances
Online Access:https://www.oejournal.org/article/doi/10.29026/oea.2024.240158
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Incorporating polarization in computer vision tasks provides new solutions to high-level analytics, in particular when coupled with machine learning frameworks such as convolutional neural networks (CNN). A recent review in Opto-Electronic Science reports on the developments in data-driven polarimetric imaging, including polarimetric descattering, 3D imaging, reflection removal, target detection and biomedical imaging. The review carefully analyzes these new trends with their advantages and disadvantages, and provides a general insight for future research and development.
ISSN:2096-4579