Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015796515> ?p ?o ?g. }
- W3015796515 abstract "Recovering sharp video sequence from a motion-blurred image is highly ill-posed due to the significant loss of motion information in the blurring process. For event-based cameras, however, fast motion can be captured as events at high time rate, raising new opportunities to exploring effective solutions. In this paper, we start from a sequential formulation of event-based motion deblurring, then show how its optimization can be unfolded with a novel end-to-end deep architecture. The proposed architecture is a convolutional recurrent neural network that integrates visual and temporal knowledge of both global and local scales in principled manner. To further improve the reconstruction, we propose a differentiable directional event filtering module to effectively extract rich boundary prior from the stream of events. We conduct extensive experiments on the synthetic GoPro dataset and a large newly introduced dataset captured by a DAVIS240C camera. The proposed approach achieves state-of-the-art reconstruction quality, and generalizes better to handling real-world motion blur." @default.
- W3015796515 created "2020-04-17" @default.
- W3015796515 creator A5020276561 @default.
- W3015796515 creator A5032875389 @default.
- W3015796515 creator A5039109630 @default.
- W3015796515 creator A5046790720 @default.
- W3015796515 creator A5071773009 @default.
- W3015796515 creator A5073535763 @default.
- W3015796515 date "2020-04-13" @default.
- W3015796515 modified "2023-10-12" @default.
- W3015796515 title "Learning Event-Based Motion Deblurring" @default.
- W3015796515 cites W1485009520 @default.
- W3015796515 cites W1598281290 @default.
- W3015796515 cites W1899439299 @default.
- W3015796515 cites W1916935112 @default.
- W3015796515 cites W1976730913 @default.
- W3015796515 cites W2016574277 @default.
- W3015796515 cites W2099628070 @default.
- W3015796515 cites W2118456997 @default.
- W3015796515 cites W2132244934 @default.
- W3015796515 cites W2152922098 @default.
- W3015796515 cites W2300657047 @default.
- W3015796515 cites W233979554 @default.
- W3015796515 cites W2472115300 @default.
- W3015796515 cites W2474628748 @default.
- W3015796515 cites W2519597608 @default.
- W3015796515 cites W2560533888 @default.
- W3015796515 cites W2564023417 @default.
- W3015796515 cites W2579111433 @default.
- W3015796515 cites W2586480386 @default.
- W3015796515 cites W2605737038 @default.
- W3015796515 cites W2613155248 @default.
- W3015796515 cites W2740543610 @default.
- W3015796515 cites W2776004874 @default.
- W3015796515 cites W2777685367 @default.
- W3015796515 cites W2780534972 @default.
- W3015796515 cites W2795181989 @default.
- W3015796515 cites W2798735168 @default.
- W3015796515 cites W2798859500 @default.
- W3015796515 cites W2886787375 @default.
- W3015796515 cites W2890948304 @default.
- W3015796515 cites W2892642687 @default.
- W3015796515 cites W2899000831 @default.
- W3015796515 cites W2902490190 @default.
- W3015796515 cites W2917756165 @default.
- W3015796515 cites W2963093735 @default.
- W3015796515 cites W2963136136 @default.
- W3015796515 cites W2963810582 @default.
- W3015796515 cites W2964030969 @default.
- W3015796515 cites W2964051148 @default.
- W3015796515 cites W2964160927 @default.
- W3015796515 cites W2964317599 @default.
- W3015796515 cites W2964615694 @default.
- W3015796515 cites W2965217508 @default.
- W3015796515 cites W2970672284 @default.
- W3015796515 cites W2996728775 @default.
- W3015796515 cites W3097980825 @default.
- W3015796515 cites W3106068969 @default.
- W3015796515 cites W764651262 @default.
- W3015796515 cites W2125566565 @default.
- W3015796515 doi "https://doi.org/10.48550/arxiv.2004.05794" @default.
- W3015796515 hasPublicationYear "2020" @default.
- W3015796515 type Work @default.
- W3015796515 sameAs 3015796515 @default.
- W3015796515 citedByCount "0" @default.
- W3015796515 crossrefType "posted-content" @default.
- W3015796515 hasAuthorship W3015796515A5020276561 @default.
- W3015796515 hasAuthorship W3015796515A5032875389 @default.
- W3015796515 hasAuthorship W3015796515A5039109630 @default.
- W3015796515 hasAuthorship W3015796515A5046790720 @default.
- W3015796515 hasAuthorship W3015796515A5071773009 @default.
- W3015796515 hasAuthorship W3015796515A5073535763 @default.
- W3015796515 hasBestOaLocation W30157965151 @default.
- W3015796515 hasConcept C104114177 @default.
- W3015796515 hasConcept C106430172 @default.
- W3015796515 hasConcept C108583219 @default.
- W3015796515 hasConcept C111919701 @default.
- W3015796515 hasConcept C115961682 @default.
- W3015796515 hasConcept C121332964 @default.
- W3015796515 hasConcept C146159030 @default.
- W3015796515 hasConcept C154945302 @default.
- W3015796515 hasConcept C2777693668 @default.
- W3015796515 hasConcept C2777708103 @default.
- W3015796515 hasConcept C2778112365 @default.
- W3015796515 hasConcept C2779662365 @default.
- W3015796515 hasConcept C31972630 @default.
- W3015796515 hasConcept C41008148 @default.
- W3015796515 hasConcept C54355233 @default.
- W3015796515 hasConcept C62520636 @default.
- W3015796515 hasConcept C81363708 @default.
- W3015796515 hasConcept C86803240 @default.
- W3015796515 hasConcept C9417928 @default.
- W3015796515 hasConcept C98045186 @default.
- W3015796515 hasConceptScore W3015796515C104114177 @default.
- W3015796515 hasConceptScore W3015796515C106430172 @default.
- W3015796515 hasConceptScore W3015796515C108583219 @default.
- W3015796515 hasConceptScore W3015796515C111919701 @default.
- W3015796515 hasConceptScore W3015796515C115961682 @default.
- W3015796515 hasConceptScore W3015796515C121332964 @default.
- W3015796515 hasConceptScore W3015796515C146159030 @default.