Skip to main content

LSHR-Net: a hardware-friendly solution for high-resolution computational imaging using a mixed-weights neural network

Bai, Fangliang, Liu, Jinchao, Liu, Xiaojuan, Osadchy, Margarita, Wang, Chao, Gibson, Stuart J. (2020) LSHR-Net: a hardware-friendly solution for high-resolution computational imaging using a mixed-weights neural network. Neurocomputing, . ISSN 0925-2312. (doi:10.1016/j.neucom.2020.04.010) (Access to this publication is currently restricted. You may be able to access a copy if URLs are provided) (KAR id:81026)

PDF Author's Accepted Manuscript
Language: English

Restricted to Repository staff only until 19 April 2021.

Creative Commons Licence
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Contact us about this Publication
[img]
Official URL
https://doi.org/10.1016/j.neucom.2020.04.010

Abstract

Recent work showed neural-network based approaches to reconstructing images from compressively sensed measurements offer significant improvements in accuracy and signal compression. Such methods can dramatically boost the capability of computational imaging hardware. However, to date, there have been two major drawbacks: (1) the high-precision real-valued sensing patterns proposed in the majority of existing works can prove problematic when used with computational imaging hardware such as a digital micromirror sampling device and (2) the network structures for image reconstruction involve intensive computation, which is also not suitable for hardware deployment. To address these problems, we propose a novel hardware-friendly solution based on mixed-weights neural networks for computational imaging. In particular, learned binary-weight sensing patterns are tailored to the sampling device. Moreover, we proposed a recursive network structure for low-resolution image sampling and high-resolution reconstruction scheme. It reduces both the required number of measurements and reconstruction computation by operating convolution on small intermediate feature maps. The recursive structure further reduced the model size, making the network more computationally efficient when deployed with the hardware. Our method has been validated on benchmark datasets and achieved state of the art reconstruction accuracy. We tested our proposed network in conjunction with a proof-of-concept hardware setup.

Item Type: Article
DOI/Identification number: 10.1016/j.neucom.2020.04.010
Uncontrolled keywords: Single pixel camera, Computational imaging, Neural network, Image reconstruction, Super resolution, Binary weights
Subjects: Q Science
Divisions: Faculties > Sciences > School of Physical Sciences
Depositing User: Stuart Gibson
Date Deposited: 28 Apr 2020 09:41 UTC
Last Modified: 28 Apr 2020 09:41 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/81026 (The current URI for this page, for reference purposes)
Gibson, Stuart J.: https://orcid.org/0000-0002-7981-241X
  • Depositors only (login required):

Downloads

Downloads per month over past year