Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201772641> ?p ?o ?g. }
- W3201772641 abstract "Although recent research has witnessed a significant progress on the video deblurring task, these methods struggle to reconcile inference efficiency and visual quality simultaneously, especially on ultra-high-definition (UHD) videos (e.g., 4K resolution). To address the problem, we propose a novel deep model for fast and accurate UHD Video Deblurring (UHDVD). The proposed UHDVD is achieved by a separable-patch architecture, which collaborates with a multi-scale integration scheme to achieve a large receptive field without adding the number of generic convolutional layers and kernels. Additionally, we design a residual channel-spatial attention (RCSA) module to improve accuracy and reduce the depth of the network appropriately. The proposed UHDVD is the first real-time deblurring model for 4K videos at 35 fps. To train the proposed model, we build a new dataset comprised of 4K blurry videos and corresponding sharp frames using three different smartphones. Comprehensive experimental results show that our network performs favorably against the state-of-the-art methods on both the 4K dataset and public benchmarks in terms of accuracy, speed, and model size." @default.
- W3201772641 created "2021-10-11" @default.
- W3201772641 creator A5052579372 @default.
- W3201772641 creator A5057999649 @default.
- W3201772641 creator A5059073535 @default.
- W3201772641 creator A5068837264 @default.
- W3201772641 creator A5084038184 @default.
- W3201772641 creator A5091053091 @default.
- W3201772641 date "2021-10-01" @default.
- W3201772641 modified "2023-10-06" @default.
- W3201772641 title "Multi-Scale Separable Network for Ultra-High-Definition Video Deblurring" @default.
- W3201772641 cites W1457323852 @default.
- W3201772641 cites W159023233 @default.
- W3201772641 cites W1916935112 @default.
- W3201772641 cites W1987075379 @default.
- W3201772641 cites W1992309968 @default.
- W3201772641 cites W2044005793 @default.
- W3201772641 cites W2118456997 @default.
- W3201772641 cites W2141115311 @default.
- W3201772641 cites W2166475174 @default.
- W3201772641 cites W2166576327 @default.
- W3201772641 cites W2167307343 @default.
- W3201772641 cites W2170188555 @default.
- W3201772641 cites W233979554 @default.
- W3201772641 cites W2560533888 @default.
- W3201772641 cites W2564023417 @default.
- W3201772641 cites W2586480386 @default.
- W3201772641 cites W2592939477 @default.
- W3201772641 cites W2798735168 @default.
- W3201772641 cites W2953823547 @default.
- W3201772641 cites W2955179830 @default.
- W3201772641 cites W2961218591 @default.
- W3201772641 cites W2963130865 @default.
- W3201772641 cites W2963312584 @default.
- W3201772641 cites W2964030969 @default.
- W3201772641 cites W2964040059 @default.
- W3201772641 cites W2964042483 @default.
- W3201772641 cites W2964051148 @default.
- W3201772641 cites W2965217508 @default.
- W3201772641 cites W2965669158 @default.
- W3201772641 cites W2982795046 @default.
- W3201772641 cites W2983118621 @default.
- W3201772641 cites W2987477823 @default.
- W3201772641 cites W3014765916 @default.
- W3201772641 cites W3034789174 @default.
- W3201772641 cites W3035086889 @default.
- W3201772641 cites W3035212231 @default.
- W3201772641 cites W3035355889 @default.
- W3201772641 cites W3035484352 @default.
- W3201772641 cites W3088065502 @default.
- W3201772641 cites W3101787898 @default.
- W3201772641 cites W3170697543 @default.
- W3201772641 cites W64052135 @default.
- W3201772641 doi "https://doi.org/10.1109/iccv48922.2021.01377" @default.
- W3201772641 hasPublicationYear "2021" @default.
- W3201772641 type Work @default.
- W3201772641 sameAs 3201772641 @default.
- W3201772641 citedByCount "8" @default.
- W3201772641 countsByYear W32017726412022 @default.
- W3201772641 countsByYear W32017726412023 @default.
- W3201772641 crossrefType "proceedings-article" @default.
- W3201772641 hasAuthorship W3201772641A5052579372 @default.
- W3201772641 hasAuthorship W3201772641A5057999649 @default.
- W3201772641 hasAuthorship W3201772641A5059073535 @default.
- W3201772641 hasAuthorship W3201772641A5068837264 @default.
- W3201772641 hasAuthorship W3201772641A5084038184 @default.
- W3201772641 hasAuthorship W3201772641A5091053091 @default.
- W3201772641 hasConcept C106430172 @default.
- W3201772641 hasConcept C108583219 @default.
- W3201772641 hasConcept C113775141 @default.
- W3201772641 hasConcept C11413529 @default.
- W3201772641 hasConcept C115961682 @default.
- W3201772641 hasConcept C121332964 @default.
- W3201772641 hasConcept C126042441 @default.
- W3201772641 hasConcept C127413603 @default.
- W3201772641 hasConcept C154945302 @default.
- W3201772641 hasConcept C155512373 @default.
- W3201772641 hasConcept C201995342 @default.
- W3201772641 hasConcept C202444582 @default.
- W3201772641 hasConcept C2776214188 @default.
- W3201772641 hasConcept C2777693668 @default.
- W3201772641 hasConcept C2778755073 @default.
- W3201772641 hasConcept C2780451532 @default.
- W3201772641 hasConcept C31972630 @default.
- W3201772641 hasConcept C33923547 @default.
- W3201772641 hasConcept C41008148 @default.
- W3201772641 hasConcept C62520636 @default.
- W3201772641 hasConcept C76155785 @default.
- W3201772641 hasConcept C9417928 @default.
- W3201772641 hasConcept C9652623 @default.
- W3201772641 hasConceptScore W3201772641C106430172 @default.
- W3201772641 hasConceptScore W3201772641C108583219 @default.
- W3201772641 hasConceptScore W3201772641C113775141 @default.
- W3201772641 hasConceptScore W3201772641C11413529 @default.
- W3201772641 hasConceptScore W3201772641C115961682 @default.
- W3201772641 hasConceptScore W3201772641C121332964 @default.
- W3201772641 hasConceptScore W3201772641C126042441 @default.
- W3201772641 hasConceptScore W3201772641C127413603 @default.
- W3201772641 hasConceptScore W3201772641C154945302 @default.
- W3201772641 hasConceptScore W3201772641C155512373 @default.