FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313598857> ?p ?o ?g. }

• W4313598857 endingPage "927" @default.
• W4313598857 startingPage "920" @default.
• W4313598857 abstract "Remarkable progress has been achieved by current depth completion approaches, which produce dense depth maps from sparse depth maps and corresponding color images. However, the performances of these approaches are limited due to the insufficient feature extractions and fusions. In this work, we propose an efficient multi-modal feature fusion based depth completion framework (MFF-Net), which can efficiently extract and fuse features with different modals in both encoding and decoding processes, thus more depth details with better performance can be obtained. In specific, the encoding process contains three branches where different modals of features from both color and sparse depth input can be extracted, and a multi-feature channel shuffle is utilized to enhance these features thus features with better representation abilities can be obtained. Meanwhile, the decoding process contains two branches to sufficiently fuse the extracted multi-modal features, and a multi-level weighted combination is employed to further enhance and fuse features with different modals, thus leading to more accurate and better refined depth maps. Extensive experiments on different benchmarks demonstrate that we achieve state-of-the-art among online methods. Meanwhile, we further evaluate the predicted dense depth by RGB-D SLAM, which is a commonly used downstream robotic perception task, and higher accuracy on vehicle's trajectory can be obtained in KITTI odometry dataset, which demonstrates the high quality of our depth prediction and the potential of improving the related downstream tasks with depth completion results." @default.
• W4313598857 created "2023-01-06" @default.
• W4313598857 creator A5012409875 @default.
• W4313598857 creator A5030165903 @default.
• W4313598857 creator A5040613309 @default.
• W4313598857 creator A5051292006 @default.
• W4313598857 creator A5061136923 @default.
• W4313598857 creator A5069683163 @default.
• W4313598857 creator A5091549331 @default.
• W4313598857 date "2023-02-01" @default.
• W4313598857 modified "2023-10-01" @default.
• W4313598857 title "MFF-Net: Towards Efficient Monocular Depth Completion With Multi-Modal Feature Fusion" @default.
• W4313598857 cites W125693051 @default.
• W4313598857 cites W2115579991 @default.
• W4313598857 cites W2194775991 @default.
• W4313598857 cites W2554243884 @default.
• W4313598857 cites W2796461436 @default.
• W4313598857 cites W2885093229 @default.
• W4313598857 cites W2899479761 @default.
• W4313598857 cites W2922509574 @default.
• W4313598857 cites W2963125010 @default.
• W4313598857 cites W2963316641 @default.
• W4313598857 cites W2963867516 @default.
• W4313598857 cites W2969202876 @default.
• W4313598857 cites W2998031326 @default.
• W4313598857 cites W3000500950 @default.
• W4313598857 cites W3003796433 @default.
• W4313598857 cites W3034726754 @default.
• W4313598857 cites W3099306897 @default.
• W4313598857 cites W3102327032 @default.
• W4313598857 cites W3105639468 @default.
• W4313598857 cites W3109128945 @default.
• W4313598857 cites W3110653837 @default.
• W4313598857 cites W3112432113 @default.
• W4313598857 cites W3126423155 @default.
• W4313598857 cites W3129248413 @default.
• W4313598857 cites W3152805691 @default.
• W4313598857 cites W3173882198 @default.
• W4313598857 cites W3174318861 @default.
• W4313598857 cites W3175561084 @default.
• W4313598857 cites W3185514162 @default.
• W4313598857 cites W3189360099 @default.
• W4313598857 cites W3205398852 @default.
• W4313598857 cites W3206335707 @default.
• W4313598857 cites W3207068520 @default.
• W4313598857 cites W4214871154 @default.
• W4313598857 cites W4221146773 @default.
• W4313598857 cites W4225303589 @default.
• W4313598857 cites W4225987522 @default.
• W4313598857 cites W4292968861 @default.
• W4313598857 cites W4312566889 @default.
• W4313598857 cites W4312793957 @default.
• W4313598857 cites W639708223 @default.
• W4313598857 doi "https://doi.org/10.1109/lra.2023.3234776" @default.
• W4313598857 hasPublicationYear "2023" @default.
• W4313598857 type Work @default.
• W4313598857 citedByCount "3" @default.
• W4313598857 countsByYear W43135988572023 @default.
• W4313598857 crossrefType "journal-article" @default.
• W4313598857 hasAuthorship W4313598857A5012409875 @default.
• W4313598857 hasAuthorship W4313598857A5030165903 @default.
• W4313598857 hasAuthorship W4313598857A5040613309 @default.
• W4313598857 hasAuthorship W4313598857A5051292006 @default.
• W4313598857 hasAuthorship W4313598857A5061136923 @default.
• W4313598857 hasAuthorship W4313598857A5069683163 @default.
• W4313598857 hasAuthorship W4313598857A5091549331 @default.
• W4313598857 hasConcept C111919701 @default.
• W4313598857 hasConcept C11413529 @default.
• W4313598857 hasConcept C119599485 @default.
• W4313598857 hasConcept C125411270 @default.
• W4313598857 hasConcept C127413603 @default.
• W4313598857 hasConcept C138885662 @default.
• W4313598857 hasConcept C141353440 @default.
• W4313598857 hasConcept C153180895 @default.
• W4313598857 hasConcept C154945302 @default.
• W4313598857 hasConcept C19966478 @default.
• W4313598857 hasConcept C2776401178 @default.
• W4313598857 hasConcept C31972630 @default.
• W4313598857 hasConcept C41008148 @default.
• W4313598857 hasConcept C41895202 @default.
• W4313598857 hasConcept C49441653 @default.
• W4313598857 hasConcept C57273362 @default.
• W4313598857 hasConcept C5799516 @default.
• W4313598857 hasConcept C65909025 @default.
• W4313598857 hasConcept C82990744 @default.
• W4313598857 hasConcept C90509273 @default.
• W4313598857 hasConcept C98045186 @default.
• W4313598857 hasConceptScore W4313598857C111919701 @default.
• W4313598857 hasConceptScore W4313598857C11413529 @default.
• W4313598857 hasConceptScore W4313598857C119599485 @default.
• W4313598857 hasConceptScore W4313598857C125411270 @default.
• W4313598857 hasConceptScore W4313598857C127413603 @default.
• W4313598857 hasConceptScore W4313598857C138885662 @default.
• W4313598857 hasConceptScore W4313598857C141353440 @default.
• W4313598857 hasConceptScore W4313598857C153180895 @default.
• W4313598857 hasConceptScore W4313598857C154945302 @default.
• W4313598857 hasConceptScore W4313598857C19966478 @default.
• W4313598857 hasConceptScore W4313598857C2776401178 @default.

• next