FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321020947> ?p ?o ?g. }

• W4321020947 endingPage "1328" @default.
• W4321020947 startingPage "1315" @default.
• W4321020947 abstract "Depth maps generally suffer from large erroneous areas even in public RGB-Depth datasets. Existing learning-based depth recovery methods are limited by insufficient high-quality datasets and optimization-based methods generally depend on local contexts not to effectively correct large erroneous areas. This paper develops an RGB-guided depth map recovery method based on the fully connected conditional random field (dense CRF) model to jointly utilize local and global contexts of depth maps and RGB images. A high-quality depth map is inferred by maximizing its probability conditioned upon a low-quality depth map and a reference RGB image based on the dense CRF model. The optimization function is composed of redesigned unary and pairwise components, which constraint local structure and global structure of depth map, respectively, with the guidance of RGB image. In addition, the texture-copy artifacts problem is handled by two-stage dense CRF models in a coarse-to-fine way. A coarse depth map is first recovered by embedding RGB image in a dense CRF model in unit of 3×3 blocks. It is refined afterward by embedding RGB image in another model in unit of individual pixels and restricting the model mainly work in discontinued regions. Extensive experiments on six datasets verify that the proposed method considerably outperforms a dozen of baseline methods in correcting erroneous areas and diminishing texture-copy artifacts of depth maps." @default.
• W4321020947 created "2023-02-17" @default.
• W4321020947 creator A5034427070 @default.
• W4321020947 creator A5037055449 @default.
• W4321020947 creator A5047405956 @default.
• W4321020947 creator A5054401766 @default.
• W4321020947 date "2023-01-01" @default.
• W4321020947 modified "2023-10-05" @default.
• W4321020947 title "RGB-Guided Depth Map Recovery by Two-Stage Coarse-to-Fine Dense CRF Models" @default.
• W4321020947 cites W1921093919 @default.
• W4321020947 cites W1974949120 @default.
• W4321020947 cites W1983044509 @default.
• W4321020947 cites W1987724871 @default.
• W4321020947 cites W1994184495 @default.
• W4321020947 cites W2020353466 @default.
• W4321020947 cites W2021851106 @default.
• W4321020947 cites W2030300879 @default.
• W4321020947 cites W2052107321 @default.
• W4321020947 cites W2099244020 @default.
• W4321020947 cites W2101131403 @default.
• W4321020947 cites W2104620097 @default.
• W4321020947 cites W2106403211 @default.
• W4321020947 cites W2110892967 @default.
• W4321020947 cites W2117248802 @default.
• W4321020947 cites W2118273112 @default.
• W4321020947 cites W2125188192 @default.
• W4321020947 cites W2132947399 @default.
• W4321020947 cites W2133665775 @default.
• W4321020947 cites W2151646056 @default.
• W4321020947 cites W2155479981 @default.
• W4321020947 cites W2195231623 @default.
• W4321020947 cites W2214189948 @default.
• W4321020947 cites W2337078182 @default.
• W4321020947 cites W2340897893 @default.
• W4321020947 cites W2342695184 @default.
• W4321020947 cites W2345227558 @default.
• W4321020947 cites W2412782625 @default.
• W4321020947 cites W2499631751 @default.
• W4321020947 cites W2520322935 @default.
• W4321020947 cites W2520953340 @default.
• W4321020947 cites W2521490062 @default.
• W4321020947 cites W2524856263 @default.
• W4321020947 cites W2528266293 @default.
• W4321020947 cites W2565639579 @default.
• W4321020947 cites W2580700891 @default.
• W4321020947 cites W2594519801 @default.
• W4321020947 cites W2741885505 @default.
• W4321020947 cites W2790567986 @default.
• W4321020947 cites W2794739174 @default.
• W4321020947 cites W2800443886 @default.
• W4321020947 cites W2892614179 @default.
• W4321020947 cites W2893425817 @default.
• W4321020947 cites W2897501237 @default.
• W4321020947 cites W2921235899 @default.
• W4321020947 cites W2949579494 @default.
• W4321020947 cites W2954174912 @default.
• W4321020947 cites W2963182372 @default.
• W4321020947 cites W2963422396 @default.
• W4321020947 cites W2963760790 @default.
• W4321020947 cites W2964339842 @default.
• W4321020947 cites W2982336692 @default.
• W4321020947 cites W2996800272 @default.
• W4321020947 cites W3019445466 @default.
• W4321020947 cites W3033193681 @default.
• W4321020947 cites W3035133372 @default.
• W4321020947 cites W3035563424 @default.
• W4321020947 cites W3038079672 @default.
• W4321020947 cites W3081167590 @default.
• W4321020947 cites W3101690711 @default.
• W4321020947 cites W4241716071 @default.
• W4321020947 cites W4297095264 @default.
• W4321020947 cites W4308190001 @default.
• W4321020947 cites W63091017 @default.
• W4321020947 doi "https://doi.org/10.1109/tip.2023.3242144" @default.
• W4321020947 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37022905" @default.
• W4321020947 hasPublicationYear "2023" @default.
• W4321020947 type Work @default.
• W4321020947 citedByCount "1" @default.
• W4321020947 countsByYear W43210209472023 @default.
• W4321020947 crossrefType "journal-article" @default.
• W4321020947 hasAuthorship W4321020947A5034427070 @default.
• W4321020947 hasAuthorship W4321020947A5037055449 @default.
• W4321020947 hasAuthorship W4321020947A5047405956 @default.
• W4321020947 hasAuthorship W4321020947A5054401766 @default.
• W4321020947 hasConcept C115961682 @default.
• W4321020947 hasConcept C141268832 @default.
• W4321020947 hasConcept C152565575 @default.
• W4321020947 hasConcept C153180895 @default.
• W4321020947 hasConcept C154945302 @default.
• W4321020947 hasConcept C160633673 @default.
• W4321020947 hasConcept C31972630 @default.
• W4321020947 hasConcept C33923547 @default.
• W4321020947 hasConcept C41008148 @default.
• W4321020947 hasConcept C41608201 @default.
• W4321020947 hasConcept C82990744 @default.
• W4321020947 hasConceptScore W4321020947C115961682 @default.
• W4321020947 hasConceptScore W4321020947C141268832 @default.
• W4321020947 hasConceptScore W4321020947C152565575 @default.

• next