Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386869582> ?p ?o ?g. }
- W4386869582 endingPage "5325" @default.
- W4386869582 startingPage "5310" @default.
- W4386869582 abstract "Recently, learning-based multi-exposure fusion (MEF) methods have made significant improvements. However, these methods mainly focus on static scenes and are prone to generate ghosting artifacts when tackling a more common scenario, i.e., the input images include motion, due to the lack of a benchmark dataset and solution for dynamic scenes. In this paper, we fill this gap by creating an MEF dataset of dynamic scenes, which contains multi-exposure image sequences and their corresponding high-quality reference images. To construct such a dataset, we propose a ‘static-for-dynamic’ strategy to obtain multi-exposure sequences with motions and their corresponding reference images. To the best of our knowledge, this is the first MEF dataset of dynamic scenes. Correspondingly, we propose a deep dynamic MEF (DDMEF) framework to reconstruct a ghost-free high-quality image from only two differently exposed images of a dynamic scene. DDMEF is achieved through two steps: pre-enhancement-based alignment and privilege-information-guided fusion. The former pre-enhances the input images before alignment, which helps to address the misalignments caused by the significant exposure difference. The latter introduces a privilege distillation scheme with an information attention transfer loss, which effectively improves the deghosting ability of the fusion network. Extensive qualitative and quantitative experimental results show that the proposed method outperforms state-of-the-art dynamic MEF methods. The source code and dataset are released at https://github.com/Tx000/Deep_dynamicMEF." @default.
- W4386869582 created "2023-09-20" @default.
- W4386869582 creator A5003931624 @default.
- W4386869582 creator A5025519877 @default.
- W4386869582 creator A5026109629 @default.
- W4386869582 creator A5030798126 @default.
- W4386869582 creator A5035108397 @default.
- W4386869582 creator A5039480817 @default.
- W4386869582 creator A5048237545 @default.
- W4386869582 creator A5055415805 @default.
- W4386869582 date "2023-01-01" @default.
- W4386869582 modified "2023-09-27" @default.
- W4386869582 title "Deep Multi-Exposure Image Fusion for Dynamic Scenes" @default.
- W4386869582 cites W1563899710 @default.
- W4386869582 cites W1580436348 @default.
- W4386869582 cites W1974871520 @default.
- W4386869582 cites W1995813543 @default.
- W4386869582 cites W1998393535 @default.
- W4386869582 cites W2013980527 @default.
- W4386869582 cites W2054273865 @default.
- W4386869582 cites W2054927225 @default.
- W4386869582 cites W2073779945 @default.
- W4386869582 cites W2074926543 @default.
- W4386869582 cites W2091484864 @default.
- W4386869582 cites W2092904050 @default.
- W4386869582 cites W2117228865 @default.
- W4386869582 cites W2296478018 @default.
- W4386869582 cites W2418999752 @default.
- W4386869582 cites W2590560192 @default.
- W4386869582 cites W2736611505 @default.
- W4386869582 cites W2752849939 @default.
- W4386869582 cites W2776574544 @default.
- W4386869582 cites W2783573276 @default.
- W4386869582 cites W2883566908 @default.
- W4386869582 cites W2890107857 @default.
- W4386869582 cites W2947338419 @default.
- W4386869582 cites W2948618171 @default.
- W4386869582 cites W2963530785 @default.
- W4386869582 cites W2963787388 @default.
- W4386869582 cites W2973555408 @default.
- W4386869582 cites W2990293450 @default.
- W4386869582 cites W2998012573 @default.
- W4386869582 cites W3016539359 @default.
- W4386869582 cites W3035441328 @default.
- W4386869582 cites W3122334470 @default.
- W4386869582 cites W3129817135 @default.
- W4386869582 cites W3131111098 @default.
- W4386869582 cites W3190808861 @default.
- W4386869582 cites W3213749391 @default.
- W4386869582 cites W4210531105 @default.
- W4386869582 cites W4210571497 @default.
- W4386869582 cites W4226178544 @default.
- W4386869582 cites W4292672210 @default.
- W4386869582 cites W4293731547 @default.
- W4386869582 cites W4295241286 @default.
- W4386869582 cites W4313318666 @default.
- W4386869582 cites W4319878464 @default.
- W4386869582 cites W4321766599 @default.
- W4386869582 cites W4321794021 @default.
- W4386869582 cites W828875492 @default.
- W4386869582 doi "https://doi.org/10.1109/tip.2023.3315123" @default.
- W4386869582 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37725730" @default.
- W4386869582 hasPublicationYear "2023" @default.
- W4386869582 type Work @default.
- W4386869582 citedByCount "0" @default.
- W4386869582 crossrefType "journal-article" @default.
- W4386869582 hasAuthorship W4386869582A5003931624 @default.
- W4386869582 hasAuthorship W4386869582A5025519877 @default.
- W4386869582 hasAuthorship W4386869582A5026109629 @default.
- W4386869582 hasAuthorship W4386869582A5030798126 @default.
- W4386869582 hasAuthorship W4386869582A5035108397 @default.
- W4386869582 hasAuthorship W4386869582A5039480817 @default.
- W4386869582 hasAuthorship W4386869582A5048237545 @default.
- W4386869582 hasAuthorship W4386869582A5055415805 @default.
- W4386869582 hasConcept C108583219 @default.
- W4386869582 hasConcept C115961682 @default.
- W4386869582 hasConcept C120665830 @default.
- W4386869582 hasConcept C121332964 @default.
- W4386869582 hasConcept C13280743 @default.
- W4386869582 hasConcept C138885662 @default.
- W4386869582 hasConcept C154945302 @default.
- W4386869582 hasConcept C158525013 @default.
- W4386869582 hasConcept C177264268 @default.
- W4386869582 hasConcept C185798385 @default.
- W4386869582 hasConcept C192209626 @default.
- W4386869582 hasConcept C199360897 @default.
- W4386869582 hasConcept C205649164 @default.
- W4386869582 hasConcept C2776760102 @default.
- W4386869582 hasConcept C2780531524 @default.
- W4386869582 hasConcept C31972630 @default.
- W4386869582 hasConcept C41008148 @default.
- W4386869582 hasConcept C41895202 @default.
- W4386869582 hasConcept C69744172 @default.
- W4386869582 hasConceptScore W4386869582C108583219 @default.
- W4386869582 hasConceptScore W4386869582C115961682 @default.
- W4386869582 hasConceptScore W4386869582C120665830 @default.
- W4386869582 hasConceptScore W4386869582C121332964 @default.
- W4386869582 hasConceptScore W4386869582C13280743 @default.