Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897501237> ?p ?o ?g. }
- W2897501237 endingPage "1006" @default.
- W2897501237 startingPage "994" @default.
- W2897501237 abstract "Depth image super-resolution is a significant yet challenging task. In this paper, we introduce a novel deep color guided coarse-to-fine convolutional neural network (CNN) framework to address this problem. First, we present a datadriven filter method to approximate the ideal filter for depth image super-resolution instead of hand-designed filters. Based on large data samples, the filter learned is more accurate and stable for upsampling depth image. Second, we introduce a coarse-to-fine CNN to learn different sizes of filter kernels. In coarse stage, larger filter kernels are learned by CNN to achieve crude high-resolution depth image. As to fine stage, the crude high-resolution depth image is used as the input so that smaller filter kernels are learned to gain more accurate results. Benefit from this network, we can progressively recover the high frequency details. Third, we construct a color guidance strategy that fuses color difference and spatial distance for depth image upsampling. We revise the interpolated high-resolution depth image according to the corresponding pixels in highresolution color maps. Guided by color information, the depth of high-resolution image obtained can alleviate texture copying artifacts and preserve edge details effectively. Quantitative and qualitative experimental results demonstrate our state-of-the-art performance for depth map super-resolution." @default.
- W2897501237 created "2018-10-26" @default.
- W2897501237 creator A5006980036 @default.
- W2897501237 creator A5009598072 @default.
- W2897501237 creator A5059372830 @default.
- W2897501237 creator A5068891693 @default.
- W2897501237 creator A5073975203 @default.
- W2897501237 date "2019-02-01" @default.
- W2897501237 modified "2023-10-17" @default.
- W2897501237 title "Deep Color Guided Coarse-to-Fine Convolutional Network Cascade for Depth Image Super-Resolution" @default.
- W2897501237 cites W1484539719 @default.
- W2897501237 cites W1513324323 @default.
- W2897501237 cites W1516087576 @default.
- W2897501237 cites W1529155083 @default.
- W2897501237 cites W1590360666 @default.
- W2897501237 cites W1791560514 @default.
- W2897501237 cites W1919542679 @default.
- W2897501237 cites W1930824406 @default.
- W2897501237 cites W1971918169 @default.
- W2897501237 cites W1974949120 @default.
- W2897501237 cites W1993133381 @default.
- W2897501237 cites W1994184495 @default.
- W2897501237 cites W2001395975 @default.
- W2897501237 cites W2020353466 @default.
- W2897501237 cites W2032674519 @default.
- W2897501237 cites W2039699512 @default.
- W2897501237 cites W2060280062 @default.
- W2897501237 cites W2076531691 @default.
- W2897501237 cites W2079302740 @default.
- W2897501237 cites W2088254198 @default.
- W2897501237 cites W2099244020 @default.
- W2897501237 cites W2099712288 @default.
- W2897501237 cites W2104599718 @default.
- W2897501237 cites W2104620097 @default.
- W2897501237 cites W2118273112 @default.
- W2897501237 cites W2121058967 @default.
- W2897501237 cites W2125188192 @default.
- W2897501237 cites W2127992984 @default.
- W2897501237 cites W2133255058 @default.
- W2897501237 cites W2148534289 @default.
- W2897501237 cites W2150081556 @default.
- W2897501237 cites W2153388956 @default.
- W2897501237 cites W2155479981 @default.
- W2897501237 cites W2194775991 @default.
- W2897501237 cites W2195231623 @default.
- W2897501237 cites W2242218935 @default.
- W2897501237 cites W2284980149 @default.
- W2897501237 cites W2356493088 @default.
- W2897501237 cites W2494890720 @default.
- W2897501237 cites W2520322935 @default.
- W2897501237 cites W2550158653 @default.
- W2897501237 cites W2618530766 @default.
- W2897501237 cites W2790246571 @default.
- W2897501237 cites W2794997799 @default.
- W2897501237 cites W2868292291 @default.
- W2897501237 cites W3104196124 @default.
- W2897501237 cites W4241716071 @default.
- W2897501237 cites W54257720 @default.
- W2897501237 cites W63091017 @default.
- W2897501237 cites W65809711 @default.
- W2897501237 doi "https://doi.org/10.1109/tip.2018.2874285" @default.
- W2897501237 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30296229" @default.
- W2897501237 hasPublicationYear "2019" @default.
- W2897501237 type Work @default.
- W2897501237 sameAs 2897501237 @default.
- W2897501237 citedByCount "85" @default.
- W2897501237 countsByYear W28975012372018 @default.
- W2897501237 countsByYear W28975012372019 @default.
- W2897501237 countsByYear W28975012372020 @default.
- W2897501237 countsByYear W28975012372021 @default.
- W2897501237 countsByYear W28975012372022 @default.
- W2897501237 countsByYear W28975012372023 @default.
- W2897501237 crossrefType "journal-article" @default.
- W2897501237 hasAuthorship W2897501237A5006980036 @default.
- W2897501237 hasAuthorship W2897501237A5009598072 @default.
- W2897501237 hasAuthorship W2897501237A5059372830 @default.
- W2897501237 hasAuthorship W2897501237A5068891693 @default.
- W2897501237 hasAuthorship W2897501237A5073975203 @default.
- W2897501237 hasBestOaLocation W28975012372 @default.
- W2897501237 hasConcept C106131492 @default.
- W2897501237 hasConcept C110384440 @default.
- W2897501237 hasConcept C115961682 @default.
- W2897501237 hasConcept C141268832 @default.
- W2897501237 hasConcept C142616399 @default.
- W2897501237 hasConcept C153180895 @default.
- W2897501237 hasConcept C154945302 @default.
- W2897501237 hasConcept C156140930 @default.
- W2897501237 hasConcept C160633673 @default.
- W2897501237 hasConcept C205372480 @default.
- W2897501237 hasConcept C31972630 @default.
- W2897501237 hasConcept C41008148 @default.
- W2897501237 hasConcept C81363708 @default.
- W2897501237 hasConcept C9417928 @default.
- W2897501237 hasConceptScore W2897501237C106131492 @default.
- W2897501237 hasConceptScore W2897501237C110384440 @default.
- W2897501237 hasConceptScore W2897501237C115961682 @default.
- W2897501237 hasConceptScore W2897501237C141268832 @default.
- W2897501237 hasConceptScore W2897501237C142616399 @default.