Paper
4 April 2023 Generative adversarial networks method of polarization 3D reconstruction based on meta-transfer learning
Yuxuan Mao, Kun Gao
Author Affiliations +
Proceedings Volume 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications; 126170R (2023) https://doi.org/10.1117/12.2663312
Event: 9th Symposium on Novel Photoelectronic Detection Technology and Applications (NDTA 2022), 2022, Hefei, China
Abstract
This paper makes a first attempt to combines meta-transfer learning and generative adversarial networks (GAN) technology to solve the Shape from Polarization (SfP) problem. To solve this physics-based ill-posed problem, some researchers choose to blend these physical models as priors into a neural network architecture however cannot meet the requirements of cross-domain and few-shot polarization data. This proposed approach put forward two innovative points. First, we design the meta-transfer method so adapt GAN for few-shot learning tasks. Second, we introduce physical priors between monocular polarization sequence and 3D normal vector into the generative loss term. We report to exceed the previous state-of-the-art on deepsfp dataset, showing the potential of meta-transfer learning in few-shot generative tasks.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yuxuan Mao and Kun Gao "Generative adversarial networks method of polarization 3D reconstruction based on meta-transfer learning", Proc. SPIE 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications, 126170R (4 April 2023); https://doi.org/10.1117/12.2663312
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Polarization

Gallium nitride

3D modeling

3D acquisition

3D image processing

Target detection

Data modeling

RELATED CONTENT

Recognizing 3D objects in cluttered backgrounds
Proceedings of SPIE (September 23 2003)
Approach for 3D volumes matching
Proceedings of SPIE (April 04 2001)

Back to Top