FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308190001> ?p ?o ?g. }

• W4308190001 endingPage "7035" @default.
• W4308190001 startingPage "7020" @default.
• W4308190001 abstract "Depth maps acquired by either physical sensors or learning methods are often seriously distorted due to boundary distortion problems, including missing, fake, and misaligned boundaries (compared with RGB images). An RGB-guided depth map recovery method is proposed in this paper to recover true boundaries in seriously distorted depth maps. Therefore, a unified model is first developed to observe all these kinds of distorted boundaries in depth maps. Observing distorted boundaries is equivalent to identifying erroneous regions in distorted depth maps, because depth boundaries are essentially formed by contiguous regions with different intensities. Then, erroneous regions are identified by separately extracting local structures of RGB image and depth map with Gaussian kernels and comparing their similarity on the basis of the SSIM index. A depth map recovery method is then proposed on the basis of the unified model. This method recovers true depth boundaries by iteratively identifying and correcting erroneous regions in recovered depth map based on the unified model and a weighted median filter. Because RGB image generally includes additional textural contents compared with depth maps, texture-copy artifacts problem is further addressed in the proposed method by restricting the model works around depth boundaries in each iteration. Extensive experiments are conducted on five RGB-depth datasets including depth map recovery, depth super-resolution, depth estimation enhancement, and depth completion enhancement. The results demonstrate that the proposed method considerably improves both the quantitative and visual qualities of recovered depth maps in comparison with fifteen competitive methods. Most object boundaries in recovered depth maps are corrected accurately, and kept sharply and well aligned with the ones in RGB images." @default.
• W4308190001 created "2022-11-09" @default.
• W4308190001 creator A5006277484 @default.
• W4308190001 creator A5034427070 @default.
• W4308190001 creator A5037055449 @default.
• W4308190001 creator A5047405956 @default.
• W4308190001 creator A5054401766 @default.
• W4308190001 date "2022-01-01" @default.
• W4308190001 modified "2023-10-14" @default.
• W4308190001 title "Depth Map Recovery Based on a Unified Depth Boundary Distortion Model" @default.
• W4308190001 cites W1803059841 @default.
• W4308190001 cites W1964370383 @default.
• W4308190001 cites W1974949120 @default.
• W4308190001 cites W1983044509 @default.
• W4308190001 cites W1987724871 @default.
• W4308190001 cites W1994184495 @default.
• W4308190001 cites W2015207482 @default.
• W4308190001 cites W2017302992 @default.
• W4308190001 cites W2020353466 @default.
• W4308190001 cites W2030300879 @default.
• W4308190001 cites W2038349953 @default.
• W4308190001 cites W2052107321 @default.
• W4308190001 cites W2086835035 @default.
• W4308190001 cites W2099244020 @default.
• W4308190001 cites W2106403211 @default.
• W4308190001 cites W2107884096 @default.
• W4308190001 cites W2110892967 @default.
• W4308190001 cites W2117248802 @default.
• W4308190001 cites W2118273112 @default.
• W4308190001 cites W2125188192 @default.
• W4308190001 cites W2132715474 @default.
• W4308190001 cites W2133665775 @default.
• W4308190001 cites W2134227763 @default.
• W4308190001 cites W2145023731 @default.
• W4308190001 cites W2151646056 @default.
• W4308190001 cites W2155479981 @default.
• W4308190001 cites W2221366145 @default.
• W4308190001 cites W2257456433 @default.
• W4308190001 cites W2337078182 @default.
• W4308190001 cites W2345227558 @default.
• W4308190001 cites W2486979733 @default.
• W4308190001 cites W2499631751 @default.
• W4308190001 cites W2520953340 @default.
• W4308190001 cites W2521490062 @default.
• W4308190001 cites W2524856263 @default.
• W4308190001 cites W2790567986 @default.
• W4308190001 cites W2794739174 @default.
• W4308190001 cites W2798727000 @default.
• W4308190001 cites W2800443886 @default.
• W4308190001 cites W2893425817 @default.
• W4308190001 cites W2921235899 @default.
• W4308190001 cites W2963182372 @default.
• W4308190001 cites W2964014680 @default.
• W4308190001 cites W2969202876 @default.
• W4308190001 cites W2973110888 @default.
• W4308190001 cites W2986701260 @default.
• W4308190001 cites W2996800272 @default.
• W4308190001 cites W3019445466 @default.
• W4308190001 cites W3033193681 @default.
• W4308190001 cites W3034953156 @default.
• W4308190001 cites W3035563424 @default.
• W4308190001 cites W3038079672 @default.
• W4308190001 cites W3081167590 @default.
• W4308190001 cites W3101690711 @default.
• W4308190001 cites W4241716071 @default.
• W4308190001 cites W63091017 @default.
• W4308190001 doi "https://doi.org/10.1109/tip.2022.3216768" @default.
• W4308190001 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36331641" @default.
• W4308190001 hasPublicationYear "2022" @default.
• W4308190001 type Work @default.
• W4308190001 citedByCount "5" @default.
• W4308190001 countsByYear W43081900012023 @default.
• W4308190001 crossrefType "journal-article" @default.
• W4308190001 hasAuthorship W4308190001A5006277484 @default.
• W4308190001 hasAuthorship W4308190001A5034427070 @default.
• W4308190001 hasAuthorship W4308190001A5037055449 @default.
• W4308190001 hasAuthorship W4308190001A5047405956 @default.
• W4308190001 hasAuthorship W4308190001A5054401766 @default.
• W4308190001 hasConcept C115961682 @default.
• W4308190001 hasConcept C12426560 @default.
• W4308190001 hasConcept C126780896 @default.
• W4308190001 hasConcept C134306372 @default.
• W4308190001 hasConcept C141268832 @default.
• W4308190001 hasConcept C153180895 @default.
• W4308190001 hasConcept C154945302 @default.
• W4308190001 hasConcept C194257627 @default.
• W4308190001 hasConcept C2524010 @default.
• W4308190001 hasConcept C2776257435 @default.
• W4308190001 hasConcept C31258907 @default.
• W4308190001 hasConcept C31972630 @default.
• W4308190001 hasConcept C33923547 @default.
• W4308190001 hasConcept C41008148 @default.
• W4308190001 hasConcept C62354387 @default.
• W4308190001 hasConcept C82990744 @default.
• W4308190001 hasConceptScore W4308190001C115961682 @default.
• W4308190001 hasConceptScore W4308190001C12426560 @default.
• W4308190001 hasConceptScore W4308190001C126780896 @default.
• W4308190001 hasConceptScore W4308190001C134306372 @default.

• next