FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379649592> ?p ?o ?g. }

• W4379649592 abstract "Abstract Deep learning has recently been proven to deliver excellent performance in multi-view stereo (MVS). However, it is difficult for deep learning-based MVS approaches to balance their efficiency and effectiveness. Towards this end, we propose the DSC-MVSNet, a novel coarse-to-fine and end-to-end framework for more efficient and more accurate depth estimation in MVS. In particular, we propose an attention aware 3D UNet-shape network, which first uses the depthwise separable convolutions for cost volume regularization. This mechanism enables effective aggregation of information and significantly reduces the model parameters and computation by transforming the ordinary convolution on cost volume as depthwise convolution and pointwise convolution. Besides, a 3D-Attention module is proposed to alleviate the feature mismatching problem in cost volume regularization and aggregate the important information of cost volume in three dimensions (i.e. channel, space, and depth). Moreover, we propose an efficient Feature Transfer Module to upsample the low-resolution (LR) depth map to a high-resolution (HR) depth map to achieve higher accuracy. With extensive experiments on two benchmark datasets, i.e. DTU and Tanks & Temples, we demonstrate that the parameters of our model are significantly reduced to $$25%$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML> <mml:mrow> <mml:mn>25</mml:mn> <mml:mo>%</mml:mo> </mml:mrow> </mml:math> of the state-of-the-art model MVSNet. Besides, our method outperforms or maintains on par accuracy with the state-of-the-art models. Our source code is available at https://github.com/zs670980918/DSC-MVSNet ." @default.
• W4379649592 created "2023-06-08" @default.
• W4379649592 creator A5018606597 @default.
• W4379649592 creator A5056429995 @default.
• W4379649592 creator A5056646929 @default.
• W4379649592 creator A5057777785 @default.
• W4379649592 creator A5065917738 @default.
• W4379649592 creator A5068147366 @default.
• W4379649592 creator A5090606294 @default.
• W4379649592 date "2023-06-07" @default.
• W4379649592 modified "2023-10-14" @default.
• W4379649592 title "DSC-MVSNet: attention aware cost volume regularization based on depthwise separable convolution for multi-view stereo" @default.
• W4379649592 cites W1536680647 @default.
• W4379649592 cites W1539230104 @default.
• W4379649592 cites W179875071 @default.
• W4379649592 cites W1974740638 @default.
• W4379649592 cites W1992642990 @default.
• W4379649592 cites W2064675550 @default.
• W4379649592 cites W2083360182 @default.
• W4379649592 cites W2085905957 @default.
• W4379649592 cites W2108417695 @default.
• W4379649592 cites W2128052895 @default.
• W4379649592 cites W2129404737 @default.
• W4379649592 cites W2156116778 @default.
• W4379649592 cites W2157494358 @default.
• W4379649592 cites W2168545424 @default.
• W4379649592 cites W2194775991 @default.
• W4379649592 cites W2205172244 @default.
• W4379649592 cites W2338968644 @default.
• W4379649592 cites W2395611524 @default.
• W4379649592 cites W2412782625 @default.
• W4379649592 cites W2476548250 @default.
• W4379649592 cites W2519683295 @default.
• W4379649592 cites W2596303892 @default.
• W4379649592 cites W2738551266 @default.
• W4379649592 cites W2799166040 @default.
• W4379649592 cites W2884585870 @default.
• W4379649592 cites W2926429807 @default.
• W4379649592 cites W2954930822 @default.
• W4379649592 cites W2962793285 @default.
• W4379649592 cites W2963163009 @default.
• W4379649592 cites W2963393688 @default.
• W4379649592 cites W2963495494 @default.
• W4379649592 cites W2963727650 @default.
• W4379649592 cites W2982169158 @default.
• W4379649592 cites W2985066174 @default.
• W4379649592 cites W2992718396 @default.
• W4379649592 cites W2997111976 @default.
• W4379649592 cites W3034524082 @default.
• W4379649592 cites W3034530552 @default.
• W4379649592 cites W3034564916 @default.
• W4379649592 cites W3034600477 @default.
• W4379649592 cites W3034643157 @default.
• W4379649592 cites W3097305369 @default.
• W4379649592 cites W3102132650 @default.
• W4379649592 cites W3108346482 @default.
• W4379649592 cites W3137737699 @default.
• W4379649592 cites W3155600845 @default.
• W4379649592 cites W3170262190 @default.
• W4379649592 cites W3204267695 @default.
• W4379649592 cites W4206760982 @default.
• W4379649592 cites W4213309271 @default.
• W4379649592 cites W639708223 @default.
• W4379649592 doi "https://doi.org/10.1007/s40747-023-01106-3" @default.
• W4379649592 hasPublicationYear "2023" @default.
• W4379649592 type Work @default.
• W4379649592 citedByCount "0" @default.
• W4379649592 crossrefType "journal-article" @default.
• W4379649592 hasAuthorship W4379649592A5018606597 @default.
• W4379649592 hasAuthorship W4379649592A5056429995 @default.
• W4379649592 hasAuthorship W4379649592A5056646929 @default.
• W4379649592 hasAuthorship W4379649592A5057777785 @default.
• W4379649592 hasAuthorship W4379649592A5065917738 @default.
• W4379649592 hasAuthorship W4379649592A5068147366 @default.
• W4379649592 hasAuthorship W4379649592A5090606294 @default.
• W4379649592 hasBestOaLocation W43796495921 @default.
• W4379649592 hasConcept C108583219 @default.
• W4379649592 hasConcept C11413529 @default.
• W4379649592 hasConcept C121332964 @default.
• W4379649592 hasConcept C127313418 @default.
• W4379649592 hasConcept C13280743 @default.
• W4379649592 hasConcept C134306372 @default.
• W4379649592 hasConcept C154945302 @default.
• W4379649592 hasConcept C185798385 @default.
• W4379649592 hasConcept C20556612 @default.
• W4379649592 hasConcept C2776135515 @default.
• W4379649592 hasConcept C2777984123 @default.
• W4379649592 hasConcept C33923547 @default.
• W4379649592 hasConcept C41008148 @default.
• W4379649592 hasConcept C45347329 @default.
• W4379649592 hasConcept C50644808 @default.
• W4379649592 hasConcept C62520636 @default.
• W4379649592 hasConcept C70710897 @default.
• W4379649592 hasConceptScore W4379649592C108583219 @default.
• W4379649592 hasConceptScore W4379649592C11413529 @default.
• W4379649592 hasConceptScore W4379649592C121332964 @default.
• W4379649592 hasConceptScore W4379649592C127313418 @default.
• W4379649592 hasConceptScore W4379649592C13280743 @default.
• W4379649592 hasConceptScore W4379649592C134306372 @default.
• W4379649592 hasConceptScore W4379649592C154945302 @default.

• next