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


Back to Top