Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295141344> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4295141344 endingPage "413" @default.
- W4295141344 startingPage "403" @default.
- W4295141344 abstract "Most state-of-the-art deep learning based depth estimation methods follow the pipeline of firstly forming a 4D cost volume (feature dimension, max disparity, height, and width) and then regressing disparity from the cost volume by several 3D convolutional layers. Applying 3D operations on the 4D tensor leads to unacceptable computational complexity and memory cost. To solve the problem, we aim at replacing the 4D cost volume with 3D cost volume so that the disparity can be regressed by 2D convolutions to achieve a good balance between efficiency and effectiveness. To this end, a light-weighted network, called PCNet, is proposed to generate 3D cost volume. The main novelty lies in the proposed Paired Channel Feature Volume (PCFV) which is capable of combining the features of stereo pairs with specially designed 3D filters to preliminarily encode the relationship between each pair of the channels. Moreover, a densely connected aggregation on the outputs of PCFV is performed to exploit much richer contextual information. Experimental results on the SceneFlow, KITTI 2012, and KITTI 2015 datasets demonstrate that the proposed PCNet achieves comparable accuracy with state-of-the-art methods and keeps high efficiency as well." @default.
- W4295141344 created "2022-09-11" @default.
- W4295141344 creator A5025861927 @default.
- W4295141344 creator A5037129512 @default.
- W4295141344 creator A5069704364 @default.
- W4295141344 creator A5086887025 @default.
- W4295141344 date "2022-12-01" @default.
- W4295141344 modified "2023-10-17" @default.
- W4295141344 title "PCNet: Paired channel feature volume network for accurate and efficient depth estimation" @default.
- W4295141344 cites W2112421488 @default.
- W4295141344 cites W2117248802 @default.
- W4295141344 cites W2148534289 @default.
- W4295141344 cites W2782278879 @default.
- W4295141344 cites W2900790473 @default.
- W4295141344 cites W3000764918 @default.
- W4295141344 cites W3090896893 @default.
- W4295141344 cites W3104104444 @default.
- W4295141344 cites W3110568504 @default.
- W4295141344 cites W3116474649 @default.
- W4295141344 cites W3125237740 @default.
- W4295141344 cites W3135576287 @default.
- W4295141344 cites W3195364887 @default.
- W4295141344 cites W3212593512 @default.
- W4295141344 doi "https://doi.org/10.1016/j.neucom.2022.09.024" @default.
- W4295141344 hasPublicationYear "2022" @default.
- W4295141344 type Work @default.
- W4295141344 citedByCount "0" @default.
- W4295141344 crossrefType "journal-article" @default.
- W4295141344 hasAuthorship W4295141344A5025861927 @default.
- W4295141344 hasAuthorship W4295141344A5037129512 @default.
- W4295141344 hasAuthorship W4295141344A5069704364 @default.
- W4295141344 hasAuthorship W4295141344A5086887025 @default.
- W4295141344 hasConcept C11413529 @default.
- W4295141344 hasConcept C121332964 @default.
- W4295141344 hasConcept C127162648 @default.
- W4295141344 hasConcept C138885662 @default.
- W4295141344 hasConcept C153180895 @default.
- W4295141344 hasConcept C154945302 @default.
- W4295141344 hasConcept C165696696 @default.
- W4295141344 hasConcept C199360897 @default.
- W4295141344 hasConcept C202444582 @default.
- W4295141344 hasConcept C20556612 @default.
- W4295141344 hasConcept C2776401178 @default.
- W4295141344 hasConcept C31258907 @default.
- W4295141344 hasConcept C33676613 @default.
- W4295141344 hasConcept C33923547 @default.
- W4295141344 hasConcept C38652104 @default.
- W4295141344 hasConcept C41008148 @default.
- W4295141344 hasConcept C41895202 @default.
- W4295141344 hasConcept C43521106 @default.
- W4295141344 hasConcept C62520636 @default.
- W4295141344 hasConcept C81363708 @default.
- W4295141344 hasConceptScore W4295141344C11413529 @default.
- W4295141344 hasConceptScore W4295141344C121332964 @default.
- W4295141344 hasConceptScore W4295141344C127162648 @default.
- W4295141344 hasConceptScore W4295141344C138885662 @default.
- W4295141344 hasConceptScore W4295141344C153180895 @default.
- W4295141344 hasConceptScore W4295141344C154945302 @default.
- W4295141344 hasConceptScore W4295141344C165696696 @default.
- W4295141344 hasConceptScore W4295141344C199360897 @default.
- W4295141344 hasConceptScore W4295141344C202444582 @default.
- W4295141344 hasConceptScore W4295141344C20556612 @default.
- W4295141344 hasConceptScore W4295141344C2776401178 @default.
- W4295141344 hasConceptScore W4295141344C31258907 @default.
- W4295141344 hasConceptScore W4295141344C33676613 @default.
- W4295141344 hasConceptScore W4295141344C33923547 @default.
- W4295141344 hasConceptScore W4295141344C38652104 @default.
- W4295141344 hasConceptScore W4295141344C41008148 @default.
- W4295141344 hasConceptScore W4295141344C41895202 @default.
- W4295141344 hasConceptScore W4295141344C43521106 @default.
- W4295141344 hasConceptScore W4295141344C62520636 @default.
- W4295141344 hasConceptScore W4295141344C81363708 @default.
- W4295141344 hasLocation W42951413441 @default.
- W4295141344 hasOpenAccess W4295141344 @default.
- W4295141344 hasPrimaryLocation W42951413441 @default.
- W4295141344 hasRelatedWork W2175746458 @default.
- W4295141344 hasRelatedWork W2732542196 @default.
- W4295141344 hasRelatedWork W2738221750 @default.
- W4295141344 hasRelatedWork W2758063741 @default.
- W4295141344 hasRelatedWork W2760085659 @default.
- W4295141344 hasRelatedWork W2883200793 @default.
- W4295141344 hasRelatedWork W2912288872 @default.
- W4295141344 hasRelatedWork W2940661641 @default.
- W4295141344 hasRelatedWork W3012978760 @default.
- W4295141344 hasRelatedWork W3093612317 @default.
- W4295141344 hasVolume "514" @default.
- W4295141344 isParatext "false" @default.
- W4295141344 isRetracted "false" @default.
- W4295141344 workType "article" @default.