Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015969791> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W3015969791 abstract "High Dynamic Range (HDR) reconstruction is the process of producing an HDR image from a set of Standard Dynamic Range (SDR) images with different exposure times. This is a particularly challenging problem when relative camera or object motion exists between the available SDR images. Recently, deep learning methods, specifically those based on convolutional neural networks (CNNs) have been developed for HDR and shown to achieve unprecedented quality gains. Invariably an image alignment phase precedes the CNN mapping and merging. In practice, this alignment step greatly increases the computational burden of deep HDR methods often rendering them unsuitable for real-time composition. We propose a new deep HDR technique that does not need any explicit alignment of SDR images. Instead, a novel attention mask is developed that enables the network to focus on parts of the scene with considerable motion. Further, a dense merger is proposed that leads to an economical network. Evaluation over benchmark databases reveals that the proposed AttenDense network achieves high quality HDR results with significantly reduced computation time than state of the art. Further, the incorporation of domain knowledge (development of a custom attention mask) allows a more graceful decay in performance in the face of limited training." @default.
- W3015969791 created "2020-04-17" @default.
- W3015969791 creator A5014013504 @default.
- W3015969791 creator A5087732060 @default.
- W3015969791 date "2020-05-01" @default.
- W3015969791 modified "2023-09-23" @default.
- W3015969791 title "Attention-Mask Dense Merger (Attendense) Deep HDR for Ghost Removal" @default.
- W3015969791 cites W1918272075 @default.
- W3015969791 cites W1988735598 @default.
- W3015969791 cites W1995813543 @default.
- W3015969791 cites W2013980527 @default.
- W3015969791 cites W2054927225 @default.
- W3015969791 cites W2064619906 @default.
- W3015969791 cites W2560474170 @default.
- W3015969791 cites W2566600232 @default.
- W3015969791 cites W2582596720 @default.
- W3015969791 cites W2590560192 @default.
- W3015969791 cites W2736611505 @default.
- W3015969791 cites W2766400329 @default.
- W3015969791 cites W2766497195 @default.
- W3015969791 cites W2793788258 @default.
- W3015969791 cites W2897143711 @default.
- W3015969791 cites W2912011558 @default.
- W3015969791 cites W2922141058 @default.
- W3015969791 cites W2963446712 @default.
- W3015969791 cites W2963882477 @default.
- W3015969791 cites W2986695366 @default.
- W3015969791 cites W3106301376 @default.
- W3015969791 doi "https://doi.org/10.1109/icassp40776.2020.9053180" @default.
- W3015969791 hasPublicationYear "2020" @default.
- W3015969791 type Work @default.
- W3015969791 sameAs 3015969791 @default.
- W3015969791 citedByCount "8" @default.
- W3015969791 countsByYear W30159697912021 @default.
- W3015969791 countsByYear W30159697912022 @default.
- W3015969791 crossrefType "proceedings-article" @default.
- W3015969791 hasAuthorship W3015969791A5014013504 @default.
- W3015969791 hasAuthorship W3015969791A5087732060 @default.
- W3015969791 hasConcept C121684516 @default.
- W3015969791 hasConcept C154945302 @default.
- W3015969791 hasConcept C31972630 @default.
- W3015969791 hasConcept C41008148 @default.
- W3015969791 hasConceptScore W3015969791C121684516 @default.
- W3015969791 hasConceptScore W3015969791C154945302 @default.
- W3015969791 hasConceptScore W3015969791C31972630 @default.
- W3015969791 hasConceptScore W3015969791C41008148 @default.
- W3015969791 hasLocation W30159697911 @default.
- W3015969791 hasOpenAccess W3015969791 @default.
- W3015969791 hasPrimaryLocation W30159697911 @default.
- W3015969791 hasRelatedWork W1891287906 @default.
- W3015969791 hasRelatedWork W1969923398 @default.
- W3015969791 hasRelatedWork W2036807459 @default.
- W3015969791 hasRelatedWork W2058170566 @default.
- W3015969791 hasRelatedWork W2166044122 @default.
- W3015969791 hasRelatedWork W2229312674 @default.
- W3015969791 hasRelatedWork W258625772 @default.
- W3015969791 hasRelatedWork W2755342338 @default.
- W3015969791 hasRelatedWork W2772917594 @default.
- W3015969791 hasRelatedWork W3116076068 @default.
- W3015969791 isParatext "false" @default.
- W3015969791 isRetracted "false" @default.
- W3015969791 magId "3015969791" @default.
- W3015969791 workType "article" @default.