FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385343733> ?p ?o ?g. }

• W4385343733 abstract "Abstract Dense depth information can be reconstructed from stereo images using conventional hand-crafted as well as deep learning-based approaches. While deep-learning methods often show superior results compared to hand-crafted ones, they commonly learn geometric principles underlying the matching task from scratch and neglect that these principles have already been intensively studied and were considered explicitly in various models with great success in the past. In consequence, a broad range of principles and associated features need to be learned, limiting the possibility to focus on important details to also succeed in challenging image regions, such as close to depth discontinuities, thin objects and in weakly textured areas. To overcome this limitation, in this work, a hybrid technique, i.e., a combination of conventional hand-crafted and deep learning-based methods, is presented, addressing the task of dense stereo matching. More precisely, the input RGB stereo images are supplemented by a fourth image channel containing feature information obtained with a method based on expert knowledge. In addition, the assumption that edges in an image and discontinuities in the corresponding depth map coincide is modeled explicitly, allowing to predict the probability of being located next to a depth discontinuity per pixel. This information is used to guide the matching process and helps to sharpen correct depth discontinuities and to avoid the false prediction of such discontinuities, especially in weakly textured areas. The performance of the proposed method is investigated on three different data sets, including studies on the influence of the two methodological components as well as on the generalization capability. The results demonstrate that the presented hybrid approach can help to mitigate common limitations of deep learning-based methods and improves the quality of the estimated depth maps." @default.
• W4385343733 created "2023-07-29" @default.
• W4385343733 creator A5000550463 @default.
• W4385343733 creator A5068101057 @default.
• W4385343733 creator A5092560126 @default.
• W4385343733 date "2023-07-28" @default.
• W4385343733 modified "2023-09-25" @default.
• W4385343733 title "Guiding Deep Learning with Expert Knowledge for Dense Stereo Matching" @default.
• W4385343733 cites W125693051 @default.
• W4385343733 cites W1674866864 @default.
• W4385343733 cites W1901129140 @default.
• W4385343733 cites W2104974755 @default.
• W4385343733 cites W2117248802 @default.
• W4385343733 cites W2145023731 @default.
• W4385343733 cites W2150066425 @default.
• W4385343733 cites W2163352848 @default.
• W4385343733 cites W2166489002 @default.
• W4385343733 cites W2188695318 @default.
• W4385343733 cites W2296589133 @default.
• W4385343733 cites W2440384215 @default.
• W4385343733 cites W2583968476 @default.
• W4385343733 cites W2587715001 @default.
• W4385343733 cites W2604231069 @default.
• W4385343733 cites W2621526417 @default.
• W4385343733 cites W2887479417 @default.
• W4385343733 cites W2888898946 @default.
• W4385343733 cites W2920327301 @default.
• W4385343733 cites W2940612399 @default.
• W4385343733 cites W2952813711 @default.
• W4385343733 cites W2963043051 @default.
• W4385343733 cites W2963231581 @default.
• W4385343733 cites W2963619659 @default.
• W4385343733 cites W2963881378 @default.
• W4385343733 cites W2974878728 @default.
• W4385343733 cites W2975809251 @default.
• W4385343733 cites W2980467688 @default.
• W4385343733 cites W3040139283 @default.
• W4385343733 cites W3048548052 @default.
• W4385343733 cites W3082498369 @default.
• W4385343733 cites W3100388886 @default.
• W4385343733 cites W3112139896 @default.
• W4385343733 cites W3115742440 @default.
• W4385343733 cites W3181256344 @default.
• W4385343733 cites W3195680177 @default.
• W4385343733 cites W4200409224 @default.
• W4385343733 cites W4214714189 @default.
• W4385343733 cites W4226265017 @default.
• W4385343733 cites W4280629766 @default.
• W4385343733 cites W63091017 @default.
• W4385343733 doi "https://doi.org/10.1007/s41064-023-00252-0" @default.
• W4385343733 hasPublicationYear "2023" @default.
• W4385343733 type Work @default.
• W4385343733 citedByCount "0" @default.
• W4385343733 crossrefType "journal-article" @default.
• W4385343733 hasAuthorship W4385343733A5000550463 @default.
• W4385343733 hasAuthorship W4385343733A5068101057 @default.
• W4385343733 hasAuthorship W4385343733A5092560126 @default.
• W4385343733 hasBestOaLocation W43853437331 @default.
• W4385343733 hasConcept C105795698 @default.
• W4385343733 hasConcept C108583219 @default.
• W4385343733 hasConcept C111919701 @default.
• W4385343733 hasConcept C115961682 @default.
• W4385343733 hasConcept C120665830 @default.
• W4385343733 hasConcept C121332964 @default.
• W4385343733 hasConcept C134306372 @default.
• W4385343733 hasConcept C138885662 @default.
• W4385343733 hasConcept C153180895 @default.
• W4385343733 hasConcept C154945302 @default.
• W4385343733 hasConcept C15627037 @default.
• W4385343733 hasConcept C160633673 @default.
• W4385343733 hasConcept C162324750 @default.
• W4385343733 hasConcept C165064840 @default.
• W4385343733 hasConcept C187736073 @default.
• W4385343733 hasConcept C192209626 @default.
• W4385343733 hasConcept C2776401178 @default.
• W4385343733 hasConcept C2777042112 @default.
• W4385343733 hasConcept C2780451532 @default.
• W4385343733 hasConcept C31972630 @default.
• W4385343733 hasConcept C33923547 @default.
• W4385343733 hasConcept C41008148 @default.
• W4385343733 hasConcept C41895202 @default.
• W4385343733 hasConcept C82990744 @default.
• W4385343733 hasConcept C98045186 @default.
• W4385343733 hasConceptScore W4385343733C105795698 @default.
• W4385343733 hasConceptScore W4385343733C108583219 @default.
• W4385343733 hasConceptScore W4385343733C111919701 @default.
• W4385343733 hasConceptScore W4385343733C115961682 @default.
• W4385343733 hasConceptScore W4385343733C120665830 @default.
• W4385343733 hasConceptScore W4385343733C121332964 @default.
• W4385343733 hasConceptScore W4385343733C134306372 @default.
• W4385343733 hasConceptScore W4385343733C138885662 @default.
• W4385343733 hasConceptScore W4385343733C153180895 @default.
• W4385343733 hasConceptScore W4385343733C154945302 @default.
• W4385343733 hasConceptScore W4385343733C15627037 @default.
• W4385343733 hasConceptScore W4385343733C160633673 @default.
• W4385343733 hasConceptScore W4385343733C162324750 @default.
• W4385343733 hasConceptScore W4385343733C165064840 @default.
• W4385343733 hasConceptScore W4385343733C187736073 @default.
• W4385343733 hasConceptScore W4385343733C192209626 @default.
• W4385343733 hasConceptScore W4385343733C2776401178 @default.

• next