Presentation
9 March 2022 Computational 3D imaging with micro optics and data-driven deep learning reconstruction
Feng Tian, Weijian Yang
Author Affiliations +
Proceedings Volume PC12019, AI and Optical Data Sciences III; PC1201908 (2022) https://doi.org/10.1117/12.2610250
Event: SPIE OPTO, 2022, San Francisco, California, United States
Abstract
We present a thin camera which encodes 3D scenes into the 2D image sensor through a single piece of thin custom-fabricated microlens array and reconstructs the 3D scenes through a deep learning framework. The microlens array is designed to have a balanced frequency support among different spatial frequency. The deep learning framework is assisted with an adversarial learning model, and has a high speed in reconstruction. We validate the system in both simulations and experiments. Our thin 3D camera demonstrates the great potential of combining custom-designed micro-optics and deep learning algorithms in computational imaging.
Conference Presentation
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Feng Tian and Weijian Yang "Computational 3D imaging with micro optics and data-driven deep learning reconstruction", Proc. SPIE PC12019, AI and Optical Data Sciences III, PC1201908 (9 March 2022); https://doi.org/10.1117/12.2610250
Advertisement
Advertisement
KEYWORDS
Micro optics

Imaging systems

Reconstruction algorithms

Computational imaging

Stereoscopy

Cameras

Computing systems

Back to Top