Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226443431> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4226443431 abstract "Spectral super-resolution (SSR) refers to the hyperspectral image (HSI) recovery from an RGB counterpart. Due to the one-to-many nature of the SSR problem, a single RGB image can be reprojected to many HSIs. The key to tackle this ill-posed problem is to plug into multi-source prior information such as the natural spatial context-prior of RGB images, deep feature-prior or inherent statistical-prior of HSIs, etc., so as to effectively alleviate the degree of ill-posedness. However, most current approaches only consider the general and limited priors in their customized convolutional neural networks (CNNs), which leads to the inability to guarantee the confidence and fidelity of reconstructed spectra. In this paper, we propose a novel holistic prior-embedded relation network (HPRN) to integrate comprehensive priors to regularize and optimize the solution space of SSR. Basically, the core framework is delicately assembled by several multi-residual relation blocks (MRBs) that fully facilitate the transmission and utilization of the low-frequency content prior of RGBs. Innovatively, the semantic prior of RGB inputs is introduced to mark category attributes, and a semantic-driven spatial relation module (SSRM) is invented to perform the feature aggregation of clustered similar range for refining recovered characteristics. Additionally, we develop a transformer-based channel relation module (TCRM), which breaks the habit of employing scalars as the descriptors of channel-wise relations in the previous deep feature-prior, and replaces them with certain vectors to make the mapping function more robust and smoother. In order to maintain the mathematical correlation and spectral consistency between hyperspectral bands, the second-order prior constraints (SOPC) are incorporated into the loss function to guide the HSI reconstruction." @default.
- W4226443431 created "2022-05-05" @default.
- W4226443431 creator A5002210100 @default.
- W4226443431 creator A5033017179 @default.
- W4226443431 creator A5066057809 @default.
- W4226443431 creator A5067798266 @default.
- W4226443431 creator A5089012283 @default.
- W4226443431 date "2021-12-29" @default.
- W4226443431 modified "2023-10-16" @default.
- W4226443431 title "HPRN: Holistic Prior-embedded Relation Network for Spectral Super-Resolution" @default.
- W4226443431 doi "https://doi.org/10.48550/arxiv.2112.14608" @default.
- W4226443431 hasPublicationYear "2021" @default.
- W4226443431 type Work @default.
- W4226443431 citedByCount "0" @default.
- W4226443431 crossrefType "posted-content" @default.
- W4226443431 hasAuthorship W4226443431A5002210100 @default.
- W4226443431 hasAuthorship W4226443431A5033017179 @default.
- W4226443431 hasAuthorship W4226443431A5066057809 @default.
- W4226443431 hasAuthorship W4226443431A5067798266 @default.
- W4226443431 hasAuthorship W4226443431A5089012283 @default.
- W4226443431 hasBestOaLocation W42264434311 @default.
- W4226443431 hasConcept C107673813 @default.
- W4226443431 hasConcept C124101348 @default.
- W4226443431 hasConcept C138885662 @default.
- W4226443431 hasConcept C153180895 @default.
- W4226443431 hasConcept C154945302 @default.
- W4226443431 hasConcept C159078339 @default.
- W4226443431 hasConcept C166957645 @default.
- W4226443431 hasConcept C177769412 @default.
- W4226443431 hasConcept C205649164 @default.
- W4226443431 hasConcept C25343380 @default.
- W4226443431 hasConcept C27511587 @default.
- W4226443431 hasConcept C2776401178 @default.
- W4226443431 hasConcept C2779343474 @default.
- W4226443431 hasConcept C41008148 @default.
- W4226443431 hasConcept C41895202 @default.
- W4226443431 hasConcept C81363708 @default.
- W4226443431 hasConcept C82990744 @default.
- W4226443431 hasConcept C83665646 @default.
- W4226443431 hasConceptScore W4226443431C107673813 @default.
- W4226443431 hasConceptScore W4226443431C124101348 @default.
- W4226443431 hasConceptScore W4226443431C138885662 @default.
- W4226443431 hasConceptScore W4226443431C153180895 @default.
- W4226443431 hasConceptScore W4226443431C154945302 @default.
- W4226443431 hasConceptScore W4226443431C159078339 @default.
- W4226443431 hasConceptScore W4226443431C166957645 @default.
- W4226443431 hasConceptScore W4226443431C177769412 @default.
- W4226443431 hasConceptScore W4226443431C205649164 @default.
- W4226443431 hasConceptScore W4226443431C25343380 @default.
- W4226443431 hasConceptScore W4226443431C27511587 @default.
- W4226443431 hasConceptScore W4226443431C2776401178 @default.
- W4226443431 hasConceptScore W4226443431C2779343474 @default.
- W4226443431 hasConceptScore W4226443431C41008148 @default.
- W4226443431 hasConceptScore W4226443431C41895202 @default.
- W4226443431 hasConceptScore W4226443431C81363708 @default.
- W4226443431 hasConceptScore W4226443431C82990744 @default.
- W4226443431 hasConceptScore W4226443431C83665646 @default.
- W4226443431 hasLocation W42264434311 @default.
- W4226443431 hasOpenAccess W4226443431 @default.
- W4226443431 hasPrimaryLocation W42264434311 @default.
- W4226443431 hasRelatedWork W1972370106 @default.
- W4226443431 hasRelatedWork W1990895816 @default.
- W4226443431 hasRelatedWork W2036586713 @default.
- W4226443431 hasRelatedWork W2052253960 @default.
- W4226443431 hasRelatedWork W2129407136 @default.
- W4226443431 hasRelatedWork W2147802381 @default.
- W4226443431 hasRelatedWork W2170946361 @default.
- W4226443431 hasRelatedWork W2434955731 @default.
- W4226443431 hasRelatedWork W3197541072 @default.
- W4226443431 hasRelatedWork W2480412556 @default.
- W4226443431 isParatext "false" @default.
- W4226443431 isRetracted "false" @default.
- W4226443431 workType "article" @default.