Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288064793> ?p ?o ?g. }
- W4288064793 endingPage "33" @default.
- W4288064793 startingPage "19" @default.
- W4288064793 abstract "This article proposes a variant of a convolutional neural network-based stereo matching method, StereoPairFree, that requires only normal and not left or right stereo images. The corresponding image patches for training stereo matching cost networks look similar, apart from some properties, such as different illumination, occlusion, distortion, and foreshortening. We propose a method for generating synthesized pairs of corresponding image patches for a given image patch. We also propose a multipatch matching cost network that exploits various input patch sizes. The proposed matching cost network is optimized by cross-based cost aggregation and semiglobal matching, followed by consistency checks and bilateral filtering. Hence, StereoPairFree does not require a single stereo pair but standard images to build a deep learning stereo matching method. It is the first stereo matching method constructed from normal images and significantly outperforms monocular stereo matching approaches (Hur and Roth, 2020), (Hur and Roth, 2021), (Schuster et al., 2020). We evaluated StereoPairFree with the KITTI-2012, KITTI-2015, and Middlebury datasets. It significantly outperformed the baseline and several deep learning-based methods using these datasets." @default.
- W4288064793 created "2022-07-28" @default.
- W4288064793 creator A5001629441 @default.
- W4288064793 creator A5026344546 @default.
- W4288064793 date "2023-01-01" @default.
- W4288064793 modified "2023-10-16" @default.
- W4288064793 title "StereoPairFree: Self-Constructed Stereo Correspondence Network From Natural Images" @default.
- W4288064793 cites W1597928342 @default.
- W4288064793 cites W1674866864 @default.
- W4288064793 cites W1910044562 @default.
- W4288064793 cites W1921093919 @default.
- W4288064793 cites W1996126470 @default.
- W4288064793 cites W2012540029 @default.
- W4288064793 cites W2028852396 @default.
- W4288064793 cites W2051938740 @default.
- W4288064793 cites W2076739175 @default.
- W4288064793 cites W2090949637 @default.
- W4288064793 cites W2105466713 @default.
- W4288064793 cites W2112815111 @default.
- W4288064793 cites W2113873920 @default.
- W4288064793 cites W2117248802 @default.
- W4288064793 cites W2121781154 @default.
- W4288064793 cites W2137017911 @default.
- W4288064793 cites W2140200866 @default.
- W4288064793 cites W2143188062 @default.
- W4288064793 cites W2144041313 @default.
- W4288064793 cites W2148452478 @default.
- W4288064793 cites W2150066425 @default.
- W4288064793 cites W2151103935 @default.
- W4288064793 cites W2155488967 @default.
- W4288064793 cites W2156163116 @default.
- W4288064793 cites W2168538937 @default.
- W4288064793 cites W2214868166 @default.
- W4288064793 cites W2278323648 @default.
- W4288064793 cites W2286655030 @default.
- W4288064793 cites W2333165903 @default.
- W4288064793 cites W2341900193 @default.
- W4288064793 cites W2440384215 @default.
- W4288064793 cites W2468172454 @default.
- W4288064793 cites W2514653544 @default.
- W4288064793 cites W2554232633 @default.
- W4288064793 cites W2559178909 @default.
- W4288064793 cites W2559827556 @default.
- W4288064793 cites W2604231069 @default.
- W4288064793 cites W2738441955 @default.
- W4288064793 cites W2742117567 @default.
- W4288064793 cites W2774796680 @default.
- W4288064793 cites W2776033207 @default.
- W4288064793 cites W2779124836 @default.
- W4288064793 cites W2784652921 @default.
- W4288064793 cites W2883040756 @default.
- W4288064793 cites W2886944874 @default.
- W4288064793 cites W2887123368 @default.
- W4288064793 cites W2894742520 @default.
- W4288064793 cites W2946608878 @default.
- W4288064793 cites W2963496125 @default.
- W4288064793 cites W2963537624 @default.
- W4288064793 cites W2963619659 @default.
- W4288064793 cites W2964116251 @default.
- W4288064793 cites W3034642839 @default.
- W4288064793 cites W3100388886 @default.
- W4288064793 cites W3106635087 @default.
- W4288064793 cites W3113357670 @default.
- W4288064793 cites W3138182915 @default.
- W4288064793 cites W3173561529 @default.
- W4288064793 cites W4234282793 @default.
- W4288064793 cites W4242237682 @default.
- W4288064793 cites W1671992522 @default.
- W4288064793 doi "https://doi.org/10.1109/mis.2022.3193697" @default.
- W4288064793 hasPublicationYear "2023" @default.
- W4288064793 type Work @default.
- W4288064793 citedByCount "1" @default.
- W4288064793 countsByYear W42880647932023 @default.
- W4288064793 crossrefType "journal-article" @default.
- W4288064793 hasAuthorship W4288064793A5001629441 @default.
- W4288064793 hasAuthorship W4288064793A5026344546 @default.
- W4288064793 hasConcept C105795698 @default.
- W4288064793 hasConcept C115961682 @default.
- W4288064793 hasConcept C126780896 @default.
- W4288064793 hasConcept C153180895 @default.
- W4288064793 hasConcept C154945302 @default.
- W4288064793 hasConcept C165064840 @default.
- W4288064793 hasConcept C194257627 @default.
- W4288064793 hasConcept C2776257435 @default.
- W4288064793 hasConcept C2776436953 @default.
- W4288064793 hasConcept C2987632653 @default.
- W4288064793 hasConcept C31258907 @default.
- W4288064793 hasConcept C31451488 @default.
- W4288064793 hasConcept C31972630 @default.
- W4288064793 hasConcept C33923547 @default.
- W4288064793 hasConcept C41008148 @default.
- W4288064793 hasConcept C65909025 @default.
- W4288064793 hasConcept C68537008 @default.
- W4288064793 hasConcept C81363708 @default.
- W4288064793 hasConceptScore W4288064793C105795698 @default.
- W4288064793 hasConceptScore W4288064793C115961682 @default.
- W4288064793 hasConceptScore W4288064793C126780896 @default.
- W4288064793 hasConceptScore W4288064793C153180895 @default.