Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996756905> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2996756905 endingPage "38854" @default.
- W2996756905 startingPage "38846" @default.
- W2996756905 abstract "In public spaces such as zoos and sports facilities, the presence of fences often annoys tourists and professional photographers. There is a demand for a post-processing tool to produce a non-occluded view from an image or video. This “de-fencing” task is divided into two stages: one to detect fence regions and the other to fill the missing part. For over a decade, various methods have been proposed for video-based de-fencing. However, only a few single-image-based methods are proposed. In this paper, we focus on single-image fence removal. Conventional approaches suffer from inaccurate and non-robust fence detection and inpainting due to less content information. To solve these problems, we combine novel methods based on a deep convolutional neural network (CNN) and classical domain knowledge in image processing. In the training process, we are required to obtain both fence images and corresponding non-fence ground truth images. Therefore, we synthesize natural fence images from real images. Moreover, spacial filtering processing (e.g. a Laplacian filter and a Gaussian filter) improves the performance of the CNN for detection and inpainting. Our proposed method can automatically detect a fence and generate a clean image without any user input. Experimental results demonstrate that our method is effective for a broad range of fence images." @default.
- W2996756905 created "2019-12-26" @default.
- W2996756905 creator A5016311487 @default.
- W2996756905 creator A5090181402 @default.
- W2996756905 date "2020-01-01" @default.
- W2996756905 modified "2023-10-10" @default.
- W2996756905 title "Single-Image Fence Removal Using Deep Convolutional Neural Network" @default.
- W2996756905 cites W1521461170 @default.
- W2996756905 cites W1903029394 @default.
- W2996756905 cites W1998956470 @default.
- W2996756905 cites W2022238106 @default.
- W2996756905 cites W2052094314 @default.
- W2996756905 cites W2056933304 @default.
- W2996756905 cites W2105038642 @default.
- W2996756905 cites W2117519317 @default.
- W2996756905 cites W2121927366 @default.
- W2996756905 cites W2131394160 @default.
- W2996756905 cites W2194775991 @default.
- W2996756905 cites W2242218935 @default.
- W2996756905 cites W2288997049 @default.
- W2996756905 cites W2470163766 @default.
- W2996756905 cites W2508457857 @default.
- W2996756905 cites W2509784253 @default.
- W2996756905 cites W2525054030 @default.
- W2996756905 cites W2810552350 @default.
- W2996756905 cites W2963881378 @default.
- W2996756905 cites W2964177954 @default.
- W2996756905 cites W2964197347 @default.
- W2996756905 doi "https://doi.org/10.1109/access.2019.2960087" @default.
- W2996756905 hasPublicationYear "2020" @default.
- W2996756905 type Work @default.
- W2996756905 sameAs 2996756905 @default.
- W2996756905 citedByCount "12" @default.
- W2996756905 countsByYear W29967569052020 @default.
- W2996756905 countsByYear W29967569052021 @default.
- W2996756905 countsByYear W29967569052022 @default.
- W2996756905 countsByYear W29967569052023 @default.
- W2996756905 crossrefType "journal-article" @default.
- W2996756905 hasAuthorship W2996756905A5016311487 @default.
- W2996756905 hasAuthorship W2996756905A5090181402 @default.
- W2996756905 hasBestOaLocation W29967569051 @default.
- W2996756905 hasConcept C114614502 @default.
- W2996756905 hasConcept C115961682 @default.
- W2996756905 hasConcept C153180895 @default.
- W2996756905 hasConcept C154945302 @default.
- W2996756905 hasConcept C2779652578 @default.
- W2996756905 hasConcept C31972630 @default.
- W2996756905 hasConcept C33923547 @default.
- W2996756905 hasConcept C41008148 @default.
- W2996756905 hasConcept C81363708 @default.
- W2996756905 hasConceptScore W2996756905C114614502 @default.
- W2996756905 hasConceptScore W2996756905C115961682 @default.
- W2996756905 hasConceptScore W2996756905C153180895 @default.
- W2996756905 hasConceptScore W2996756905C154945302 @default.
- W2996756905 hasConceptScore W2996756905C2779652578 @default.
- W2996756905 hasConceptScore W2996756905C31972630 @default.
- W2996756905 hasConceptScore W2996756905C33923547 @default.
- W2996756905 hasConceptScore W2996756905C41008148 @default.
- W2996756905 hasConceptScore W2996756905C81363708 @default.
- W2996756905 hasLocation W29967569051 @default.
- W2996756905 hasOpenAccess W2996756905 @default.
- W2996756905 hasPrimaryLocation W29967569051 @default.
- W2996756905 hasRelatedWork W2175746458 @default.
- W2996756905 hasRelatedWork W2613736958 @default.
- W2996756905 hasRelatedWork W2732542196 @default.
- W2996756905 hasRelatedWork W2738221750 @default.
- W2996756905 hasRelatedWork W2760085659 @default.
- W2996756905 hasRelatedWork W2912288872 @default.
- W2996756905 hasRelatedWork W3012978760 @default.
- W2996756905 hasRelatedWork W3081496756 @default.
- W2996756905 hasRelatedWork W3093612317 @default.
- W2996756905 hasRelatedWork W4239686595 @default.
- W2996756905 hasVolume "8" @default.
- W2996756905 isParatext "false" @default.
- W2996756905 isRetracted "false" @default.
- W2996756905 magId "2996756905" @default.
- W2996756905 workType "article" @default.