FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214862245> ?p ?o ?g. }

• W4214862245 endingPage "922" @default.
• W4214862245 startingPage "912" @default.
• W4214862245 abstract "Learning-based stereomatching methods have produced remarkable results in recent years. However, typical supervised learning-based methods always suffer from the non-negligible problem of costly and time-consuming depth annotations. To mitigate this issue, in this work, a multi-stage unsupervised stereo matching method based on the cascaded Siamese network is proposed. To obtain a better performance on depth annotations, the improvements of this work are as follows. Firstly, sparse costs are constructed to predict the coarse disparity, and an adaptive sampling strategy is developed to dynamically adjust the sampling interval and effectively narrow the disparity search range. The proposed cost sparse and sampling strategy can certainly guarantee the accuracy of disparity estimation under the limited memory requirements. Then, geometric constraints with left and right semantic features are integrated into the loss function to learn the inherent matching correspondences. Next, information entropy of the probability volume is used to measure the quality of estimated disparity and designed as weighted guidance for the photometric loss. Finally, a pixel-wise disparity refinement module is designed to achieve high-resolution disparity estimation at the final stage. Experimental results on the datasets, including SceneFlow and KITTI, show the effectiveness and practicability of our method with limited memory consumption and running time." @default.
• W4214862245 created "2022-03-05" @default.
• W4214862245 creator A5011681810 @default.
• W4214862245 creator A5013976478 @default.
• W4214862245 creator A5024767647 @default.
• W4214862245 creator A5057964928 @default.
• W4214862245 creator A5070954480 @default.
• W4214862245 date "2023-01-01" @default.
• W4214862245 modified "2023-10-01" @default.
• W4214862245 title "Adaptive Cost Volume Representation for Unsupervised High-Resolution Stereo Matching" @default.
• W4214862245 cites W1803059841 @default.
• W4214862245 cites W1992178727 @default.
• W4214862245 cites W2300779272 @default.
• W4214862245 cites W2340897893 @default.
• W4214862245 cites W2520707372 @default.
• W4214862245 cites W2559827556 @default.
• W4214862245 cites W2604231069 @default.
• W4214862245 cites W2609883120 @default.
• W4214862245 cites W2883040756 @default.
• W4214862245 cites W2886944874 @default.
• W4214862245 cites W2890949887 @default.
• W4214862245 cites W2926429807 @default.
• W4214862245 cites W2946608878 @default.
• W4214862245 cites W2963517541 @default.
• W4214862245 cites W2963619659 @default.
• W4214862245 cites W2963652981 @default.
• W4214862245 cites W2963872790 @default.
• W4214862245 cites W2967693513 @default.
• W4214862245 cites W2976021265 @default.
• W4214862245 cites W2985775862 @default.
• W4214862245 cites W3004166074 @default.
• W4214862245 cites W3034308492 @default.
• W4214862245 cites W3034514115 @default.
• W4214862245 cites W3039448353 @default.
• W4214862245 cites W3100388886 @default.
• W4214862245 cites W3108346482 @default.
• W4214862245 cites W3134257222 @default.
• W4214862245 doi "https://doi.org/10.1109/tiv.2022.3155469" @default.
• W4214862245 hasPublicationYear "2023" @default.
• W4214862245 type Work @default.
• W4214862245 citedByCount "5" @default.
• W4214862245 countsByYear W42148622452022 @default.
• W4214862245 countsByYear W42148622452023 @default.
• W4214862245 crossrefType "journal-article" @default.
• W4214862245 hasAuthorship W4214862245A5011681810 @default.
• W4214862245 hasAuthorship W4214862245A5013976478 @default.
• W4214862245 hasAuthorship W4214862245A5024767647 @default.
• W4214862245 hasAuthorship W4214862245A5057964928 @default.
• W4214862245 hasAuthorship W4214862245A5070954480 @default.
• W4214862245 hasConcept C105795698 @default.
• W4214862245 hasConcept C106131492 @default.
• W4214862245 hasConcept C106301342 @default.
• W4214862245 hasConcept C121332964 @default.
• W4214862245 hasConcept C140779682 @default.
• W4214862245 hasConcept C153180895 @default.
• W4214862245 hasConcept C154945302 @default.
• W4214862245 hasConcept C159985019 @default.
• W4214862245 hasConcept C165064840 @default.
• W4214862245 hasConcept C192562407 @default.
• W4214862245 hasConcept C19499675 @default.
• W4214862245 hasConcept C204323151 @default.
• W4214862245 hasConcept C2781395549 @default.
• W4214862245 hasConcept C31972630 @default.
• W4214862245 hasConcept C33923547 @default.
• W4214862245 hasConcept C41008148 @default.
• W4214862245 hasConcept C62520636 @default.
• W4214862245 hasConceptScore W4214862245C105795698 @default.
• W4214862245 hasConceptScore W4214862245C106131492 @default.
• W4214862245 hasConceptScore W4214862245C106301342 @default.
• W4214862245 hasConceptScore W4214862245C121332964 @default.
• W4214862245 hasConceptScore W4214862245C140779682 @default.
• W4214862245 hasConceptScore W4214862245C153180895 @default.
• W4214862245 hasConceptScore W4214862245C154945302 @default.
• W4214862245 hasConceptScore W4214862245C159985019 @default.
• W4214862245 hasConceptScore W4214862245C165064840 @default.
• W4214862245 hasConceptScore W4214862245C192562407 @default.
• W4214862245 hasConceptScore W4214862245C19499675 @default.
• W4214862245 hasConceptScore W4214862245C204323151 @default.
• W4214862245 hasConceptScore W4214862245C2781395549 @default.
• W4214862245 hasConceptScore W4214862245C31972630 @default.
• W4214862245 hasConceptScore W4214862245C33923547 @default.
• W4214862245 hasConceptScore W4214862245C41008148 @default.
• W4214862245 hasConceptScore W4214862245C62520636 @default.
• W4214862245 hasFunder F4320321001 @default.
• W4214862245 hasIssue "1" @default.
• W4214862245 hasLocation W42148622451 @default.
• W4214862245 hasOpenAccess W4214862245 @default.
• W4214862245 hasPrimaryLocation W42148622451 @default.
• W4214862245 hasRelatedWork W1582396021 @default.
• W4214862245 hasRelatedWork W1991602789 @default.
• W4214862245 hasRelatedWork W2033914206 @default.
• W4214862245 hasRelatedWork W2038693912 @default.
• W4214862245 hasRelatedWork W2042327336 @default.
• W4214862245 hasRelatedWork W2046077695 @default.
• W4214862245 hasRelatedWork W2146076056 @default.
• W4214862245 hasRelatedWork W2163831990 @default.
• W4214862245 hasRelatedWork W2378160586 @default.
• W4214862245 hasRelatedWork W3003836766 @default.

• next