DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, Lizhi | ko |
dc.contributor.author | Sun, Chen | ko |
dc.contributor.author | Fu, Ying | ko |
dc.contributor.author | Kim, Min Hyuk | ko |
dc.contributor.author | Huang, Hua | ko |
dc.date.accessioned | 2019-12-13T10:29:40Z | - |
dc.date.available | 2019-12-13T10:29:40Z | - |
dc.date.created | 2019-11-11 | - |
dc.date.created | 2019-11-11 | - |
dc.date.created | 2019-11-11 | - |
dc.date.created | 2019-11-11 | - |
dc.date.created | 2019-11-11 | - |
dc.date.issued | 2019-06-16 | - |
dc.identifier.citation | 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.8024 - 8033 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10203/269390 | - |
dc.description.abstract | Regularization is a fundamental technique to solve an ill-posed optimization problem robustly and is essential to reconstruct compressive hyperspectral images. Various hand-crafted priors have been employed as a regularizer but are often insufficient to handle the wide variety of spectra of natural hyperspectral images, resulting in poor reconstruction quality. Moreover, the prior-regularized optimization requires manual tweaking of its weight parameters to achieve a balance between the spatial and spectral fidelity of result images. In this paper, we present a novel hyperspectral image reconstruction algorithm that substitutes the traditional hand-crafted prior with a data-driven prior, based on an optimization-inspired network. Our method consists of two main parts: First, we learn a novel data-driven prior that regularizes the optimization problem with a goal to boost the spatial-spectral fidelity. Our data-driven prior learns both local coherence and dynamic characteristics of natural hyperspectral images. Second, we combine our regularizer with an optimization-inspired network to overcome the heavy computation problem in the traditional iterative optimization methods. We learn the complete parameters in the network through end-to-end training, enabling robust performance with high accuracy. Extensive simulation and hardware experiments validate the superior performance of our method over the state-of-the-art methods. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior | - |
dc.type | Conference | - |
dc.identifier.wosid | 000542649301064 | - |
dc.identifier.scopusid | 2-s2.0-85073889823 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 8024 | - |
dc.citation.endingpage | 8033 | - |
dc.citation.publicationname | 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Long Beach Convention and Entertainment Center | - |
dc.identifier.doi | 10.1109/CVPR.2019.00822 | - |
dc.contributor.localauthor | Kim, Min Hyuk | - |
dc.contributor.nonIdAuthor | Wang, Lizhi | - |
dc.contributor.nonIdAuthor | Sun, Chen | - |
dc.contributor.nonIdAuthor | Fu, Ying | - |
dc.contributor.nonIdAuthor | Huang, Hua | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.