Abstract
Multi-image super-resolution (MISR) usually outperforms single-image super-resolution (SISR) under a proper inter-image alignment by explicitly exploiting the inter-image correlation. However, the large computational demand encumbers the deployment of MISR in practice. In this work, we propose a distributed optimization framework based on data parallelism for fast large-scale MISR using multi-GPU acceleration named FL-MISR. The scaled conjugate gradient (SCG) algorithm is applied to the distributed subfunctions and the local SCG variables are communicated to synchronize the convergence rate over multi-GPU systems towards a consistent convergence. Furthermore, an inner-outer border exchange scheme is performed to obviate the border effect between neighboring GPUs. The proposed FL-MISR is applied to the computed tomography (CT) system by super-resolving the projections acquired by subpixel detector shift. The SR reconstruction is performed on the fly during the CT acquisition such that no additional computation time is introduced. FL-MISR is extensively evaluated from different aspects and experimental results demonstrate that FL-MISR effectively improves the spatial resolution of CT systems in modulation transfer function (MTF) and visual perception. Comparing to a multi-core CPU implementation, FL-MISR achieves a more than 50times speedup on an off-the-shelf 4-GPU system.
Highlights
Super-resolution (SR) is a fundamental task in image processing and has been an attractive research field for decades [1,2,3]
Before we evaluate FL-Multi-image SR (MISR) on computed tomography (CT) imaging, we briefly introduce the CT system and the assessment metric
Spatial resolution of imaging systems is assessed by the modulation transfer function (MTF) which is calculated as the normalized magnitude of the Fourier Transform of the point spread function (PSF)
Summary
Super-resolution (SR) is a fundamental task in image processing and has been an attractive research field for decades [1,2,3]. Different from the deep learning-based SR methods, optimization-based MISR algorithms [23,24,25,26,27] reconstruct the latent high-resolution (HR) image explicitly based on the real acquisitions but not the training datasets. We present a multi-GPU accelerated framework for large-scale MISR reconstruction based on distributed optimization. The proposed framework is applied to the computed tomography (CT) imaging system and achieves a real-time SR reconstruction during the CT acquisition without introducing additional computation time. – We propose a distributed optimization framework for MISR, named FL-MISR, dealing with large sized images based on multi-GPU acceleration. – The proposed FL-MISR is applied to real-time CT imaging by super-resolving the projections acquired via subpixel detector shift. Comparing to a multi-core CPU implementation, FLMISR achieves a more than 50× speedup on a 4-GPU system
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
