FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387133446> ?p ?o ?g. }

• W4387133446 endingPage "8130" @default.
• W4387133446 startingPage "8130" @default.
• W4387133446 abstract "High-quality data are of utmost importance for any deep-learning application. However, acquiring such data and their annotation is challenging. This paper presents a GPU-accelerated simulator that enables the generation of high-quality, perfectly labelled data for any Time-of-Flight sensor, including LiDAR. Our approach optimally exploits the 3D graphics pipeline of the GPU, significantly decreasing data generation time while preserving compatibility with all real-time rendering engines. The presented algorithms are generic and allow users to perfectly mimic the unique sampling pattern of any such sensor. To validate our simulator, two neural networks are trained for denoising and semantic segmentation. To bridge the gap between reality and simulation, a novel loss function is introduced that requires only a small set of partially annotated real data. It enables the learning of classes for which no labels are provided in the real data, hence dramatically reducing annotation efforts. With this work, we hope to provide means for alleviating the data acquisition problem that is pertinent to deep-learning applications." @default.
• W4387133446 created "2023-09-29" @default.
• W4387133446 creator A5007570122 @default.
• W4387133446 creator A5013952510 @default.
• W4387133446 creator A5040709758 @default.
• W4387133446 creator A5046883270 @default.
• W4387133446 creator A5086939824 @default.
• W4387133446 creator A5088598176 @default.
• W4387133446 date "2023-09-28" @default.
• W4387133446 modified "2023-10-18" @default.
• W4387133446 title "GPU Rasterization-Based 3D LiDAR Simulation for Deep Learning" @default.
• W4387133446 cites W1546296816 @default.
• W4387133446 cites W1975551494 @default.
• W4387133446 cites W1982661771 @default.
• W4387133446 cites W2003114532 @default.
• W4387133446 cites W2087477843 @default.
• W4387133446 cites W2148889807 @default.
• W4387133446 cites W2150066425 @default.
• W4387133446 cites W2340897893 @default.
• W4387133446 cites W2431874326 @default.
• W4387133446 cites W2471093432 @default.
• W4387133446 cites W2531409750 @default.
• W4387133446 cites W2564755587 @default.
• W4387133446 cites W2748378127 @default.
• W4387133446 cites W2790118142 @default.
• W4387133446 cites W2798965597 @default.
• W4387133446 cites W2808892313 @default.
• W4387133446 cites W2892614179 @default.
• W4387133446 cites W2912798476 @default.
• W4387133446 cites W2946113904 @default.
• W4387133446 cites W2953421574 @default.
• W4387133446 cites W2962912109 @default.
• W4387133446 cites W2963046274 @default.
• W4387133446 cites W2963292632 @default.
• W4387133446 cites W2963730616 @default.
• W4387133446 cites W2968557240 @default.
• W4387133446 cites W3034716600 @default.
• W4387133446 cites W3035564946 @default.
• W4387133446 cites W3035574168 @default.
• W4387133446 cites W3035748168 @default.
• W4387133446 cites W3080980548 @default.
• W4387133446 cites W3084053805 @default.
• W4387133446 cites W3112943759 @default.
• W4387133446 cites W3131163716 @default.
• W4387133446 cites W3139040491 @default.
• W4387133446 cites W3168181468 @default.
• W4387133446 cites W3183784042 @default.
• W4387133446 cites W3206480303 @default.
• W4387133446 cites W3206593131 @default.
• W4387133446 cites W3212207495 @default.
• W4387133446 cites W4200152869 @default.
• W4387133446 cites W4220706531 @default.
• W4387133446 cites W4309990803 @default.
• W4387133446 cites W4312662135 @default.
• W4387133446 cites W4319301075 @default.
• W4387133446 cites W4327563557 @default.
• W4387133446 cites W4362498819 @default.
• W4387133446 cites W4362699482 @default.
• W4387133446 cites W4366420594 @default.
• W4387133446 cites W4366828666 @default.
• W4387133446 cites W4383101317 @default.
• W4387133446 cites W4385758763 @default.
• W4387133446 cites W4386057748 @default.
• W4387133446 cites W4386071758 @default.
• W4387133446 cites W4386075590 @default.
• W4387133446 cites W4386075756 @default.
• W4387133446 cites W4386076483 @default.
• W4387133446 doi "https://doi.org/10.3390/s23198130" @default.
• W4387133446 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37836959" @default.
• W4387133446 hasPublicationYear "2023" @default.
• W4387133446 type Work @default.
• W4387133446 citedByCount "0" @default.
• W4387133446 crossrefType "journal-article" @default.
• W4387133446 hasAuthorship W4387133446A5007570122 @default.
• W4387133446 hasAuthorship W4387133446A5013952510 @default.
• W4387133446 hasAuthorship W4387133446A5040709758 @default.
• W4387133446 hasAuthorship W4387133446A5046883270 @default.
• W4387133446 hasAuthorship W4387133446A5086939824 @default.
• W4387133446 hasAuthorship W4387133446A5088598176 @default.
• W4387133446 hasBestOaLocation W43871334461 @default.
• W4387133446 hasConcept C108583219 @default.
• W4387133446 hasConcept C127313418 @default.
• W4387133446 hasConcept C153083717 @default.
• W4387133446 hasConcept C154945302 @default.
• W4387133446 hasConcept C165696696 @default.
• W4387133446 hasConcept C173552908 @default.
• W4387133446 hasConcept C199360897 @default.
• W4387133446 hasConcept C205711294 @default.
• W4387133446 hasConcept C2776321320 @default.
• W4387133446 hasConcept C38652104 @default.
• W4387133446 hasConcept C41008148 @default.
• W4387133446 hasConcept C43521106 @default.
• W4387133446 hasConcept C50644808 @default.
• W4387133446 hasConcept C51399673 @default.
• W4387133446 hasConcept C62649853 @default.
• W4387133446 hasConcept C66629338 @default.
• W4387133446 hasConcept C77660652 @default.
• W4387133446 hasConcept C79403827 @default.

• next