Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964984565> ?p ?o ?g. }
- W2964984565 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." @default.
- W2964984565 created "2019-08-13" @default.
- W2964984565 creator A5019918709 @default.
- W2964984565 creator A5022334521 @default.
- W2964984565 creator A5052213409 @default.
- W2964984565 creator A5060145891 @default.
- W2964984565 creator A5067800206 @default.
- W2964984565 date "2019-06-01" @default.
- W2964984565 modified "2023-10-10" @default.
- W2964984565 title "Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior" @default.
- W2964984565 cites W1538237237 @default.
- W2964984565 cites W1550575628 @default.
- W2964984565 cites W1970762771 @default.
- W2964984565 cites W1975622988 @default.
- W2964984565 cites W2010319424 @default.
- W2964984565 cites W2010797000 @default.
- W2964984565 cites W2012946078 @default.
- W2964984565 cites W2030270830 @default.
- W2964984565 cites W2079319869 @default.
- W2964984565 cites W2084591647 @default.
- W2964984565 cites W2130184048 @default.
- W2964984565 cites W2133665775 @default.
- W2964984565 cites W2135364872 @default.
- W2964984565 cites W2144412886 @default.
- W2964984565 cites W2154761409 @default.
- W2964984565 cites W2166785998 @default.
- W2964984565 cites W2169832615 @default.
- W2964984565 cites W2170608472 @default.
- W2964984565 cites W2194775991 @default.
- W2964984565 cites W2273561594 @default.
- W2964984565 cites W2462946880 @default.
- W2964984565 cites W2511401065 @default.
- W2964984565 cites W2520430674 @default.
- W2964984565 cites W2533971697 @default.
- W2964984565 cites W2613155248 @default.
- W2964984565 cites W2766101120 @default.
- W2964984565 cites W2768964249 @default.
- W2964984565 cites W2770113520 @default.
- W2964984565 cites W2798559986 @default.
- W2964984565 cites W2903472399 @default.
- W2964984565 cites W2919115771 @default.
- W2964984565 cites W2963372104 @default.
- W2964984565 cites W2964251511 @default.
- W2964984565 cites W4233367343 @default.
- W2964984565 cites W4250955649 @default.
- W2964984565 cites W574811488 @default.
- W2964984565 doi "https://doi.org/10.1109/cvpr.2019.00822" @default.
- W2964984565 hasPublicationYear "2019" @default.
- W2964984565 type Work @default.
- W2964984565 sameAs 2964984565 @default.
- W2964984565 citedByCount "90" @default.
- W2964984565 countsByYear W29649845652019 @default.
- W2964984565 countsByYear W29649845652020 @default.
- W2964984565 countsByYear W29649845652021 @default.
- W2964984565 countsByYear W29649845652022 @default.
- W2964984565 countsByYear W29649845652023 @default.
- W2964984565 crossrefType "proceedings-article" @default.
- W2964984565 hasAuthorship W2964984565A5019918709 @default.
- W2964984565 hasAuthorship W2964984565A5022334521 @default.
- W2964984565 hasAuthorship W2964984565A5052213409 @default.
- W2964984565 hasAuthorship W2964984565A5060145891 @default.
- W2964984565 hasAuthorship W2964984565A5067800206 @default.
- W2964984565 hasConcept C107673813 @default.
- W2964984565 hasConcept C111472728 @default.
- W2964984565 hasConcept C11413529 @default.
- W2964984565 hasConcept C137836250 @default.
- W2964984565 hasConcept C138885662 @default.
- W2964984565 hasConcept C141379421 @default.
- W2964984565 hasConcept C153180895 @default.
- W2964984565 hasConcept C154945302 @default.
- W2964984565 hasConcept C159078339 @default.
- W2964984565 hasConcept C177769412 @default.
- W2964984565 hasConcept C2776135515 @default.
- W2964984565 hasConcept C31972630 @default.
- W2964984565 hasConcept C41008148 @default.
- W2964984565 hasConcept C45374587 @default.
- W2964984565 hasConcept C75553542 @default.
- W2964984565 hasConceptScore W2964984565C107673813 @default.
- W2964984565 hasConceptScore W2964984565C111472728 @default.
- W2964984565 hasConceptScore W2964984565C11413529 @default.
- W2964984565 hasConceptScore W2964984565C137836250 @default.
- W2964984565 hasConceptScore W2964984565C138885662 @default.
- W2964984565 hasConceptScore W2964984565C141379421 @default.
- W2964984565 hasConceptScore W2964984565C153180895 @default.
- W2964984565 hasConceptScore W2964984565C154945302 @default.
- W2964984565 hasConceptScore W2964984565C159078339 @default.
- W2964984565 hasConceptScore W2964984565C177769412 @default.
- W2964984565 hasConceptScore W2964984565C2776135515 @default.
- W2964984565 hasConceptScore W2964984565C31972630 @default.
- W2964984565 hasConceptScore W2964984565C41008148 @default.
- W2964984565 hasConceptScore W2964984565C45374587 @default.
- W2964984565 hasConceptScore W2964984565C75553542 @default.
- W2964984565 hasLocation W29649845651 @default.
- W2964984565 hasOpenAccess W2964984565 @default.
- W2964984565 hasPrimaryLocation W29649845651 @default.
- W2964984565 hasRelatedWork W2004054366 @default.
- W2964984565 hasRelatedWork W2010680921 @default.
- W2964984565 hasRelatedWork W2060336359 @default.
- W2964984565 hasRelatedWork W2119493293 @default.
- W2964984565 hasRelatedWork W2162939704 @default.