Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297364025> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4297364025 endingPage "107299" @default.
- W4297364025 startingPage "107299" @default.
- W4297364025 abstract "Depth estimation for light field images is crucial in light field applications such as image-based rendering and refocusing. Previous learning-based methods com bining neural network with cost volume can achieve accurate depth estimation but fail in regions with occlusion. In this paper, a two-stage attention-based occlusion-aware light field depth estimation network is proposed. In the initial depth estimation stage, the sub-aperture images are divided into four groups based on different view directions and four initial cost volumes are constructed using the feature maps from each group to aggregate initial depth maps. Then in the refined depth estimation stage, the four aggregated volumes from the initial stage are fused into one based on the view attention, where features of views with less occlusion are highly weighted to provide more effective information. Experiment results demonstrate that the proposed method can accomplish robust and accurate depth estimation in the presence of occlusion, which ranks the first place on 4D light field benchmark in terms of most accuracy metrics." @default.
- W4297364025 created "2022-09-28" @default.
- W4297364025 creator A5029960928 @default.
- W4297364025 creator A5063521420 @default.
- W4297364025 creator A5075058440 @default.
- W4297364025 date "2023-01-01" @default.
- W4297364025 modified "2023-10-16" @default.
- W4297364025 title "Occlusion-aware light field depth estimation with view attention" @default.
- W4297364025 cites W1540131840 @default.
- W4297364025 cites W2042687553 @default.
- W4297364025 cites W2064586097 @default.
- W4297364025 cites W2341651707 @default.
- W4297364025 cites W2563371362 @default.
- W4297364025 cites W2782796222 @default.
- W4297364025 cites W2783178946 @default.
- W4297364025 cites W2949362021 @default.
- W4297364025 cites W2968274502 @default.
- W4297364025 cites W3001631268 @default.
- W4297364025 cites W3004776617 @default.
- W4297364025 cites W3037034211 @default.
- W4297364025 cites W3097263996 @default.
- W4297364025 cites W3122491566 @default.
- W4297364025 cites W4312807829 @default.
- W4297364025 doi "https://doi.org/10.1016/j.optlaseng.2022.107299" @default.
- W4297364025 hasPublicationYear "2023" @default.
- W4297364025 type Work @default.
- W4297364025 citedByCount "4" @default.
- W4297364025 countsByYear W42973640252023 @default.
- W4297364025 crossrefType "journal-article" @default.
- W4297364025 hasAuthorship W4297364025A5029960928 @default.
- W4297364025 hasAuthorship W4297364025A5063521420 @default.
- W4297364025 hasAuthorship W4297364025A5075058440 @default.
- W4297364025 hasConcept C115961682 @default.
- W4297364025 hasConcept C127313418 @default.
- W4297364025 hasConcept C13280743 @default.
- W4297364025 hasConcept C138885662 @default.
- W4297364025 hasConcept C141268832 @default.
- W4297364025 hasConcept C154945302 @default.
- W4297364025 hasConcept C162324750 @default.
- W4297364025 hasConcept C164705383 @default.
- W4297364025 hasConcept C183072630 @default.
- W4297364025 hasConcept C185798385 @default.
- W4297364025 hasConcept C187736073 @default.
- W4297364025 hasConcept C205711294 @default.
- W4297364025 hasConcept C2776268601 @default.
- W4297364025 hasConcept C2776401178 @default.
- W4297364025 hasConcept C31972630 @default.
- W4297364025 hasConcept C41008148 @default.
- W4297364025 hasConcept C41895202 @default.
- W4297364025 hasConcept C48983235 @default.
- W4297364025 hasConcept C50644808 @default.
- W4297364025 hasConcept C71924100 @default.
- W4297364025 hasConcept C96250715 @default.
- W4297364025 hasConceptScore W4297364025C115961682 @default.
- W4297364025 hasConceptScore W4297364025C127313418 @default.
- W4297364025 hasConceptScore W4297364025C13280743 @default.
- W4297364025 hasConceptScore W4297364025C138885662 @default.
- W4297364025 hasConceptScore W4297364025C141268832 @default.
- W4297364025 hasConceptScore W4297364025C154945302 @default.
- W4297364025 hasConceptScore W4297364025C162324750 @default.
- W4297364025 hasConceptScore W4297364025C164705383 @default.
- W4297364025 hasConceptScore W4297364025C183072630 @default.
- W4297364025 hasConceptScore W4297364025C185798385 @default.
- W4297364025 hasConceptScore W4297364025C187736073 @default.
- W4297364025 hasConceptScore W4297364025C205711294 @default.
- W4297364025 hasConceptScore W4297364025C2776268601 @default.
- W4297364025 hasConceptScore W4297364025C2776401178 @default.
- W4297364025 hasConceptScore W4297364025C31972630 @default.
- W4297364025 hasConceptScore W4297364025C41008148 @default.
- W4297364025 hasConceptScore W4297364025C41895202 @default.
- W4297364025 hasConceptScore W4297364025C48983235 @default.
- W4297364025 hasConceptScore W4297364025C50644808 @default.
- W4297364025 hasConceptScore W4297364025C71924100 @default.
- W4297364025 hasConceptScore W4297364025C96250715 @default.
- W4297364025 hasFunder F4320325902 @default.
- W4297364025 hasLocation W42973640251 @default.
- W4297364025 hasOpenAccess W4297364025 @default.
- W4297364025 hasPrimaryLocation W42973640251 @default.
- W4297364025 hasRelatedWork W2050501141 @default.
- W4297364025 hasRelatedWork W2053392299 @default.
- W4297364025 hasRelatedWork W2082596147 @default.
- W4297364025 hasRelatedWork W2131925136 @default.
- W4297364025 hasRelatedWork W2143789285 @default.
- W4297364025 hasRelatedWork W2756963361 @default.
- W4297364025 hasRelatedWork W2771003565 @default.
- W4297364025 hasRelatedWork W3174287734 @default.
- W4297364025 hasRelatedWork W4229030109 @default.
- W4297364025 hasRelatedWork W4312301320 @default.
- W4297364025 hasVolume "160" @default.
- W4297364025 isParatext "false" @default.
- W4297364025 isRetracted "false" @default.
- W4297364025 workType "article" @default.