Data-driven polarimetric approaches fuel computational imaging expansion
Author:
- 1 January 2024
- journal article
- editorial
- Published by Opto-Electronic Advances in Opto-Electronic Advances
- Vol. 7 (9) , 240158-1-240158-3
Abstract
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.Keywords
This publication has 12 references indexed in Scilit:
- Rapid Detection of Camouflaged Artificial Target Based on Polarization Imaging and Deep LearningIEEE Photonics Journal, 2021
- Deep learning enhances polarization speckle for in vivo skin cancer detectionOptics & Laser Technology, 2021
- Deep Shape from Polarization2020
- IPLNet: a neural network for intensity-polarization imaging in low lightOptics Letters, 2020
- Polarimetric underwater image recovery via deep learningOptics and Lasers in Engineering, 2020
- HDR Reconstruction Based on the Polarization CameraIEEE Robotics and Automation Letters, 2020
- Deep Polarization Cues for Transparent Object Segmentation2020
- Separating Reflection and Transmission Images in the Wild2018
- Learning a convolutional demosaicing network for microgrid polarimeter imageryOptics Letters, 2018
- Classification of morphologically similar algae and cyanobacteria using Mueller matrix imaging and convolutional neural networksApplied Optics, 2017