Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287727818> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4287727818 abstract "Information extraction from synthetic aperture radar (SAR) images is heavily impaired by speckle noise, hence despeckling is a crucial preliminary step in scene analysis algorithms. The recent success of deep learning envisions a new generation of despeckling techniques that could outperform classical model-based methods. However, current deep learning approaches to despeckling require supervision for training, whereas clean SAR images are impossible to obtain. In the literature, this issue is tackled by resorting to either synthetically speckled optical images, which exhibit different properties with respect to true SAR images, or multi-temporal SAR images, which are difficult to acquire or fuse accurately. In this paper, inspired by recent works on blind-spot denoising networks, we propose a self-supervised Bayesian despeckling method. The proposed method is trained employing only noisy SAR images and can therefore learn features of real SAR images rather than synthetic data. Experiments show that the performance of the proposed approach is very close to the supervised training approach on synthetic data and superior on real data in both quantitative and visual assessments." @default.
- W4287727818 created "2022-07-26" @default.
- W4287727818 creator A5034486931 @default.
- W4287727818 creator A5057062750 @default.
- W4287727818 creator A5058182410 @default.
- W4287727818 creator A5062328236 @default.
- W4287727818 date "2020-07-04" @default.
- W4287727818 modified "2023-09-29" @default.
- W4287727818 title "Speckle2Void: Deep Self-Supervised SAR Despeckling with Blind-Spot Convolutional Neural Networks" @default.
- W4287727818 doi "https://doi.org/10.48550/arxiv.2007.02075" @default.
- W4287727818 hasPublicationYear "2020" @default.
- W4287727818 type Work @default.
- W4287727818 citedByCount "0" @default.
- W4287727818 crossrefType "posted-content" @default.
- W4287727818 hasAuthorship W4287727818A5034486931 @default.
- W4287727818 hasAuthorship W4287727818A5057062750 @default.
- W4287727818 hasAuthorship W4287727818A5058182410 @default.
- W4287727818 hasAuthorship W4287727818A5062328236 @default.
- W4287727818 hasBestOaLocation W42877278181 @default.
- W4287727818 hasConcept C102290492 @default.
- W4287727818 hasConcept C108583219 @default.
- W4287727818 hasConcept C115961682 @default.
- W4287727818 hasConcept C119599485 @default.
- W4287727818 hasConcept C127413603 @default.
- W4287727818 hasConcept C141353440 @default.
- W4287727818 hasConcept C153180895 @default.
- W4287727818 hasConcept C154945302 @default.
- W4287727818 hasConcept C180940675 @default.
- W4287727818 hasConcept C31972630 @default.
- W4287727818 hasConcept C41008148 @default.
- W4287727818 hasConcept C81363708 @default.
- W4287727818 hasConcept C87360688 @default.
- W4287727818 hasConcept C99498987 @default.
- W4287727818 hasConceptScore W4287727818C102290492 @default.
- W4287727818 hasConceptScore W4287727818C108583219 @default.
- W4287727818 hasConceptScore W4287727818C115961682 @default.
- W4287727818 hasConceptScore W4287727818C119599485 @default.
- W4287727818 hasConceptScore W4287727818C127413603 @default.
- W4287727818 hasConceptScore W4287727818C141353440 @default.
- W4287727818 hasConceptScore W4287727818C153180895 @default.
- W4287727818 hasConceptScore W4287727818C154945302 @default.
- W4287727818 hasConceptScore W4287727818C180940675 @default.
- W4287727818 hasConceptScore W4287727818C31972630 @default.
- W4287727818 hasConceptScore W4287727818C41008148 @default.
- W4287727818 hasConceptScore W4287727818C81363708 @default.
- W4287727818 hasConceptScore W4287727818C87360688 @default.
- W4287727818 hasConceptScore W4287727818C99498987 @default.
- W4287727818 hasLocation W42877278181 @default.
- W4287727818 hasOpenAccess W4287727818 @default.
- W4287727818 hasPrimaryLocation W42877278181 @default.
- W4287727818 hasRelatedWork W2732542196 @default.
- W4287727818 hasRelatedWork W2738221750 @default.
- W4287727818 hasRelatedWork W2773521834 @default.
- W4287727818 hasRelatedWork W2982947611 @default.
- W4287727818 hasRelatedWork W3007352029 @default.
- W4287727818 hasRelatedWork W3016152002 @default.
- W4287727818 hasRelatedWork W3118135528 @default.
- W4287727818 hasRelatedWork W3156786002 @default.
- W4287727818 hasRelatedWork W3175108991 @default.
- W4287727818 hasRelatedWork W3200905544 @default.
- W4287727818 isParatext "false" @default.
- W4287727818 isRetracted "false" @default.
- W4287727818 workType "article" @default.