FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214922651> ?p ?o ?g. }

• W4214922651 endingPage "19" @default.
• W4214922651 startingPage "1" @default.
• W4214922651 abstract "Dense stereo matching estimates the depth for each pixel of the referenced images. Recently, deep learning algorithms have dramatically promoted the development of stereo matching. The state-of-the-art result is achieved by models adopting deep convolutional neural networks. However, a considerable computational burden is also introduced, which slows the inference. To solve this problem, previous works down-sampled the input images to decrease the spatial size. However, down-sampling increases the error rate and its lower bound. In this article, we accelerate stereo matching algorithms through the improvement of network structure. Inspired by network compression, we conduct decomposition and sparsification to squeeze the computationally expensive cost optimization network. It is sparsified and then decomposed into smaller networks, which are designed and trained in a cascaded manner to reach the nearest possible performance of the larger network. Previous methods have utilized numerous refinement methods to adjust the coarse disparity. We integrate refinement methods to create an unified algorithm to utilize parallelism for running devices to further accelerate the inference. The extensive experiments on Kitti2015, Kitti2012, and Middlebury datasets demonstrate the efficiency of our method." @default.
• W4214922651 created "2022-03-05" @default.
• W4214922651 creator A5023262685 @default.
• W4214922651 creator A5071510961 @default.
• W4214922651 date "2022-03-04" @default.
• W4214922651 modified "2023-09-29" @default.
• W4214922651 title "CRAR: Accelerating Stereo Matching with Cascaded Residual Regression and Adaptive Refinement" @default.
• W4214922651 cites W1966642287 @default.
• W4214922651 cites W1996126470 @default.
• W4214922651 cites W2054536235 @default.
• W4214922651 cites W2059413159 @default.
• W4214922651 cites W2104636679 @default.
• W4214922651 cites W2104974755 @default.
• W4214922651 cites W2107082010 @default.
• W4214922651 cites W2109991658 @default.
• W4214922651 cites W2113873920 @default.
• W4214922651 cites W2115579991 @default.
• W4214922651 cites W2117248802 @default.
• W4214922651 cites W2155980617 @default.
• W4214922651 cites W2168564612 @default.
• W4214922651 cites W2194775991 @default.
• W4214922651 cites W2549571110 @default.
• W4214922651 cites W2554232633 @default.
• W4214922651 cites W2559178909 @default.
• W4214922651 cites W2728277730 @default.
• W4214922651 cites W2738441955 @default.
• W4214922651 cites W2756305021 @default.
• W4214922651 cites W2883040756 @default.
• W4214922651 cites W2895983464 @default.
• W4214922651 cites W2919115771 @default.
• W4214922651 cites W2952813711 @default.
• W4214922651 cites W2952825894 @default.
• W4214922651 cites W2962802300 @default.
• W4214922651 cites W2963231581 @default.
• W4214922651 cites W2963496125 @default.
• W4214922651 cites W2963537624 @default.
• W4214922651 cites W2963619659 @default.
• W4214922651 cites W2963872790 @default.
• W4214922651 cites W2964116251 @default.
• W4214922651 cites W2969315987 @default.
• W4214922651 cites W2997347627 @default.
• W4214922651 cites W3100388886 @default.
• W4214922651 cites W63091017 @default.
• W4214922651 cites W764651262 @default.
• W4214922651 doi "https://doi.org/10.1145/3488719" @default.
• W4214922651 hasPublicationYear "2022" @default.
• W4214922651 type Work @default.
• W4214922651 citedByCount "0" @default.
• W4214922651 crossrefType "journal-article" @default.
• W4214922651 hasAuthorship W4214922651A5023262685 @default.
• W4214922651 hasAuthorship W4214922651A5071510961 @default.
• W4214922651 hasConcept C105795698 @default.
• W4214922651 hasConcept C108583219 @default.
• W4214922651 hasConcept C11413529 @default.
• W4214922651 hasConcept C153180895 @default.
• W4214922651 hasConcept C154945302 @default.
• W4214922651 hasConcept C155512373 @default.
• W4214922651 hasConcept C165064840 @default.
• W4214922651 hasConcept C19499675 @default.
• W4214922651 hasConcept C2776214188 @default.
• W4214922651 hasConcept C2781395549 @default.
• W4214922651 hasConcept C33923547 @default.
• W4214922651 hasConcept C41008148 @default.
• W4214922651 hasConcept C50644808 @default.
• W4214922651 hasConcept C81363708 @default.
• W4214922651 hasConceptScore W4214922651C105795698 @default.
• W4214922651 hasConceptScore W4214922651C108583219 @default.
• W4214922651 hasConceptScore W4214922651C11413529 @default.
• W4214922651 hasConceptScore W4214922651C153180895 @default.
• W4214922651 hasConceptScore W4214922651C154945302 @default.
• W4214922651 hasConceptScore W4214922651C155512373 @default.
• W4214922651 hasConceptScore W4214922651C165064840 @default.
• W4214922651 hasConceptScore W4214922651C19499675 @default.
• W4214922651 hasConceptScore W4214922651C2776214188 @default.
• W4214922651 hasConceptScore W4214922651C2781395549 @default.
• W4214922651 hasConceptScore W4214922651C33923547 @default.
• W4214922651 hasConceptScore W4214922651C41008148 @default.
• W4214922651 hasConceptScore W4214922651C50644808 @default.
• W4214922651 hasConceptScore W4214922651C81363708 @default.
• W4214922651 hasFunder F4320321001 @default.
• W4214922651 hasFunder F4320335777 @default.
• W4214922651 hasFunder F4320335787 @default.
• W4214922651 hasIssue "3" @default.
• W4214922651 hasLocation W42149226511 @default.
• W4214922651 hasOpenAccess W4214922651 @default.
• W4214922651 hasPrimaryLocation W42149226511 @default.
• W4214922651 hasRelatedWork W2731899572 @default.
• W4214922651 hasRelatedWork W2732542196 @default.
• W4214922651 hasRelatedWork W2738221750 @default.
• W4214922651 hasRelatedWork W3133861977 @default.
• W4214922651 hasRelatedWork W3207322857 @default.
• W4214922651 hasRelatedWork W4200173597 @default.
• W4214922651 hasRelatedWork W4214561993 @default.
• W4214922651 hasRelatedWork W4312417841 @default.
• W4214922651 hasRelatedWork W4321369474 @default.
• W4214922651 hasRelatedWork W564581980 @default.
• W4214922651 hasVolume "18" @default.
• W4214922651 isParatext "false" @default.

• next