FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323767269> ?p ?o ?g. }

• W4323767269 endingPage "5419" @default.
• W4323767269 startingPage "5406" @default.
• W4323767269 abstract "Depth prediction is a critical problem in robotics applications especially autonomous driving. Generally, depth prediction based on binocular stereo matching and fusion of monocular image and laser point cloud are two mainstream methods. However, the former usually suffers from overfitting while building cost volume, and the latter has a limited generalization due to the lack of geometric constraint. To solve these problems, we propose a novel multimodal neural network, namely UAMD-Net, for dense depth completion based on fusion of binocular stereo matching and the weak constrain from the sparse point clouds. Specifically, the sparse point clouds are converted to sparse depth map and sent to the multimodal feature encoder (MFE) with binocular image, constructing a cross-modal cost volume. Then, it will be further processed by the multimodal feature aggregator (MFA) and the depth regression layer. Furthermore, the existing multimodal methods ignore the problem of modal dependence, that is, the network will not work when a certain modal input has a problem. Therefore, we propose a new training strategy called Modal-dropout which enables the network to be adaptively trained with multiple modal inputs and inference with specific modal inputs. Benefiting from the flexible network structure and adaptive training method, our proposed network can realize unified training under various modal input conditions. Comprehensive experiments conducted on KITTI depth completion benchmark demonstrate that our method produces robust results and outperforms other state-of-the-art methods." @default.
• W4323767269 created "2023-03-11" @default.
• W4323767269 creator A5024813614 @default.
• W4323767269 creator A5052260605 @default.
• W4323767269 creator A5058460446 @default.
• W4323767269 date "2023-10-01" @default.
• W4323767269 modified "2023-10-05" @default.
• W4323767269 title "UAMD-Net: A Unified Adaptive Multimodal Neural Network for Dense Depth Completion" @default.
• W4323767269 cites W1905829557 @default.
• W4323767269 cites W1915250530 @default.
• W4323767269 cites W2117248802 @default.
• W4323767269 cites W2150066425 @default.
• W4323767269 cites W2194775991 @default.
• W4323767269 cites W2509732761 @default.
• W4323767269 cites W2520707372 @default.
• W4323767269 cites W2531793753 @default.
• W4323767269 cites W2605938684 @default.
• W4323767269 cites W2609883120 @default.
• W4323767269 cites W2948384918 @default.
• W4323767269 cites W2962456457 @default.
• W4323767269 cites W2963192057 @default.
• W4323767269 cites W2963488291 @default.
• W4323767269 cites W2963617879 @default.
• W4323767269 cites W2963619659 @default.
• W4323767269 cites W2963652981 @default.
• W4323767269 cites W2963654727 @default.
• W4323767269 cites W2964020152 @default.
• W4323767269 cites W2969202876 @default.
• W4323767269 cites W2972581288 @default.
• W4323767269 cites W2980467688 @default.
• W4323767269 cites W2997575304 @default.
• W4323767269 cites W2998031326 @default.
• W4323767269 cites W3002983225 @default.
• W4323767269 cites W3033193681 @default.
• W4323767269 cites W3034475171 @default.
• W4323767269 cites W3034953156 @default.
• W4323767269 cites W3035333188 @default.
• W4323767269 cites W3089999934 @default.
• W4323767269 cites W3100388886 @default.
• W4323767269 cites W3106635087 @default.
• W4323767269 cites W3109128945 @default.
• W4323767269 cites W3110653837 @default.
• W4323767269 cites W3112604377 @default.
• W4323767269 cites W3118453581 @default.
• W4323767269 cites W3145609993 @default.
• W4323767269 cites W3161378645 @default.
• W4323767269 cites W3162552392 @default.
• W4323767269 cites W3165495321 @default.
• W4323767269 cites W3175561084 @default.
• W4323767269 cites W3205765322 @default.
• W4323767269 cites W3206335707 @default.
• W4323767269 cites W3206629987 @default.
• W4323767269 cites W4210294888 @default.
• W4323767269 cites W4221146773 @default.
• W4323767269 cites W4285187202 @default.
• W4323767269 cites W4312793957 @default.
• W4323767269 cites W4312852648 @default.
• W4323767269 doi "https://doi.org/10.1109/tcsvt.2023.3254650" @default.
• W4323767269 hasPublicationYear "2023" @default.
• W4323767269 type Work @default.
• W4323767269 citedByCount "0" @default.
• W4323767269 crossrefType "journal-article" @default.
• W4323767269 hasAuthorship W4323767269A5024813614 @default.
• W4323767269 hasAuthorship W4323767269A5052260605 @default.
• W4323767269 hasAuthorship W4323767269A5058460446 @default.
• W4323767269 hasBestOaLocation W43237672692 @default.
• W4323767269 hasConcept C115961682 @default.
• W4323767269 hasConcept C119857082 @default.
• W4323767269 hasConcept C131979681 @default.
• W4323767269 hasConcept C13280743 @default.
• W4323767269 hasConcept C138885662 @default.
• W4323767269 hasConcept C141268832 @default.
• W4323767269 hasConcept C154945302 @default.
• W4323767269 hasConcept C185798385 @default.
• W4323767269 hasConcept C205649164 @default.
• W4323767269 hasConcept C22019652 @default.
• W4323767269 hasConcept C2776145597 @default.
• W4323767269 hasConcept C2776401178 @default.
• W4323767269 hasConcept C31972630 @default.
• W4323767269 hasConcept C41008148 @default.
• W4323767269 hasConcept C41895202 @default.
• W4323767269 hasConcept C50644808 @default.
• W4323767269 hasConcept C65909025 @default.
• W4323767269 hasConceptScore W4323767269C115961682 @default.
• W4323767269 hasConceptScore W4323767269C119857082 @default.
• W4323767269 hasConceptScore W4323767269C131979681 @default.
• W4323767269 hasConceptScore W4323767269C13280743 @default.
• W4323767269 hasConceptScore W4323767269C138885662 @default.
• W4323767269 hasConceptScore W4323767269C141268832 @default.
• W4323767269 hasConceptScore W4323767269C154945302 @default.
• W4323767269 hasConceptScore W4323767269C185798385 @default.
• W4323767269 hasConceptScore W4323767269C205649164 @default.
• W4323767269 hasConceptScore W4323767269C22019652 @default.
• W4323767269 hasConceptScore W4323767269C2776145597 @default.
• W4323767269 hasConceptScore W4323767269C2776401178 @default.
• W4323767269 hasConceptScore W4323767269C31972630 @default.
• W4323767269 hasConceptScore W4323767269C41008148 @default.
• W4323767269 hasConceptScore W4323767269C41895202 @default.

• next