Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198777869> ?p ?o ?g. }
- W3198777869 endingPage "11665" @default.
- W3198777869 startingPage "11654" @default.
- W3198777869 abstract "In this work, a simple yet effective deep neural network is proposed to generate the dense depth map of the scene by exploiting both LiDAR sparse point cloud and the monocular camera image. Specifically, a feature pyramid network is firstly employed to extract feature maps from images across time. Then the relative pose is calculated by minimizing the feature distance between aligned pixels from inter-frame feature maps. Finally, the feature maps and the relative pose are further applied to compute the feature-metric loss for training the depth completion network. The key novelty of this work lies in that a self-supervised mechanism is presented to train the depth completion network by directly using visual-LiDAR odometry between consecutive frames. Comprehensive experiments and ablation studies on benchmark dataset KITTI demonstrate the superior performance over other state-of-the-art methods in terms of pose estimation and depth completion. The detailed performance of the proposed approach (referred to as <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>SelfCompDVLO</i> ) can be found on the KITTI depth completion benchmark. The source code, models, and data have been made available at GitHub." @default.
- W3198777869 created "2021-09-13" @default.
- W3198777869 creator A5014466286 @default.
- W3198777869 creator A5027545344 @default.
- W3198777869 creator A5037595310 @default.
- W3198777869 creator A5090587210 @default.
- W3198777869 date "2022-08-01" @default.
- W3198777869 modified "2023-10-07" @default.
- W3198777869 title "Self-Supervised Depth Completion From Direct Visual-LiDAR Odometry in Autonomous Driving" @default.
- W3198777869 cites W1512698229 @default.
- W3198777869 cites W1991544872 @default.
- W3198777869 cites W2021851106 @default.
- W3198777869 cites W2021930164 @default.
- W3198777869 cites W2076670067 @default.
- W3198777869 cites W2115579991 @default.
- W3198777869 cites W2133665775 @default.
- W3198777869 cites W2142926575 @default.
- W3198777869 cites W2193043285 @default.
- W3198777869 cites W2194775991 @default.
- W3198777869 cites W2311289276 @default.
- W3198777869 cites W2412644588 @default.
- W3198777869 cites W2474281075 @default.
- W3198777869 cites W2514653544 @default.
- W3198777869 cites W2520707372 @default.
- W3198777869 cites W2565639579 @default.
- W3198777869 cites W2738259787 @default.
- W3198777869 cites W2740480282 @default.
- W3198777869 cites W2752239616 @default.
- W3198777869 cites W2805521962 @default.
- W3198777869 cites W2886851716 @default.
- W3198777869 cites W2886968365 @default.
- W3198777869 cites W2891031479 @default.
- W3198777869 cites W2896129006 @default.
- W3198777869 cites W2904816510 @default.
- W3198777869 cites W2905494073 @default.
- W3198777869 cites W2910489334 @default.
- W3198777869 cites W2914030929 @default.
- W3198777869 cites W2914232966 @default.
- W3198777869 cites W2945016429 @default.
- W3198777869 cites W2949708697 @default.
- W3198777869 cites W2961926014 @default.
- W3198777869 cites W2963316641 @default.
- W3198777869 cites W2963416674 @default.
- W3198777869 cites W2964794620 @default.
- W3198777869 cites W2966927056 @default.
- W3198777869 cites W2969202876 @default.
- W3198777869 cites W2971726345 @default.
- W3198777869 cites W2985775862 @default.
- W3198777869 cites W2991593752 @default.
- W3198777869 cites W2992582397 @default.
- W3198777869 cites W2998293366 @default.
- W3198777869 cites W2999597893 @default.
- W3198777869 cites W3003796433 @default.
- W3198777869 cites W3007191641 @default.
- W3198777869 cites W3035510038 @default.
- W3198777869 cites W3090091644 @default.
- W3198777869 cites W3102327032 @default.
- W3198777869 doi "https://doi.org/10.1109/tits.2021.3106055" @default.
- W3198777869 hasPublicationYear "2022" @default.
- W3198777869 type Work @default.
- W3198777869 sameAs 3198777869 @default.
- W3198777869 citedByCount "5" @default.
- W3198777869 countsByYear W31987778692022 @default.
- W3198777869 countsByYear W31987778692023 @default.
- W3198777869 crossrefType "journal-article" @default.
- W3198777869 hasAuthorship W3198777869A5014466286 @default.
- W3198777869 hasAuthorship W3198777869A5027545344 @default.
- W3198777869 hasAuthorship W3198777869A5037595310 @default.
- W3198777869 hasAuthorship W3198777869A5090587210 @default.
- W3198777869 hasConcept C115961682 @default.
- W3198777869 hasConcept C127413603 @default.
- W3198777869 hasConcept C131979681 @default.
- W3198777869 hasConcept C13280743 @default.
- W3198777869 hasConcept C138885662 @default.
- W3198777869 hasConcept C141268832 @default.
- W3198777869 hasConcept C153180895 @default.
- W3198777869 hasConcept C154945302 @default.
- W3198777869 hasConcept C176217482 @default.
- W3198777869 hasConcept C185798385 @default.
- W3198777869 hasConcept C19966478 @default.
- W3198777869 hasConcept C205649164 @default.
- W3198777869 hasConcept C21547014 @default.
- W3198777869 hasConcept C2776401178 @default.
- W3198777869 hasConcept C31972630 @default.
- W3198777869 hasConcept C41008148 @default.
- W3198777869 hasConcept C41895202 @default.
- W3198777869 hasConcept C49441653 @default.
- W3198777869 hasConcept C51399673 @default.
- W3198777869 hasConcept C52102323 @default.
- W3198777869 hasConcept C52622490 @default.
- W3198777869 hasConcept C5799516 @default.
- W3198777869 hasConcept C62649853 @default.
- W3198777869 hasConcept C65909025 @default.
- W3198777869 hasConcept C90509273 @default.
- W3198777869 hasConceptScore W3198777869C115961682 @default.
- W3198777869 hasConceptScore W3198777869C127413603 @default.
- W3198777869 hasConceptScore W3198777869C131979681 @default.
- W3198777869 hasConceptScore W3198777869C13280743 @default.