FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902873058> ?p ?o ?g. }

• W2902873058 abstract "In this paper, we propose a deep learning architecture that produces accurate dense depth for the outdoor scene from a single color image and a sparse depth. Inspired by the indoor depth completion, our network estimates surface normals as the intermediate representation to produce dense depth, and can be trained end-to-end. With a modified encoder-decoder structure, our network effectively fuses the dense color image and the sparse LiDAR depth. To address outdoor specific challenges, our network predicts a confidence mask to handle mixed LiDAR signals near foreground boundaries due to occlusion, and combines estimates from the color image and surface normals with learned attention maps to improve the depth accuracy especially for distant areas. Extensive experiments demonstrate that our model improves upon the state-of-the-art performance on KITTI depth completion benchmark. Ablation study shows the positive impact of each model components to the final performance, and comprehensive analysis shows that our model generalizes well to the input with higher sparsity or from indoor scenes." @default.
• W2902873058 created "2018-12-11" @default.
• W2902873058 creator A5011794291 @default.
• W2902873058 creator A5021908609 @default.
• W2902873058 creator A5027159188 @default.
• W2902873058 creator A5039387461 @default.
• W2902873058 creator A5058136382 @default.
• W2902873058 creator A5075311772 @default.
• W2902873058 creator A5077470082 @default.
• W2902873058 date "2018-12-02" @default.
• W2902873058 modified "2023-09-23" @default.
• W2902873058 title "DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image" @default.
• W2902873058 cites W125693051 @default.
• W2902873058 cites W1545195129 @default.
• W2902873058 cites W1803059841 @default.
• W2902873058 cites W1872406745 @default.
• W2902873058 cites W1905829557 @default.
• W2902873058 cites W1956571368 @default.
• W2902873058 cites W1967027087 @default.
• W2902873058 cites W1981705310 @default.
• W2902873058 cites W1982840500 @default.
• W2902873058 cites W2005441409 @default.
• W2902873058 cites W2021191215 @default.
• W2902873058 cites W2026672030 @default.
• W2902873058 cites W2030978325 @default.
• W2902873058 cites W2074254947 @default.
• W2902873058 cites W2083047701 @default.
• W2902873058 cites W2099244020 @default.
• W2902873058 cites W2101872283 @default.
• W2902873058 cites W2102578068 @default.
• W2902873058 cites W2117751343 @default.
• W2902873058 cites W2123043875 @default.
• W2902873058 cites W2124907686 @default.
• W2902873058 cites W2125186487 @default.
• W2902873058 cites W2153388956 @default.
• W2902873058 cites W2158211626 @default.
• W2902873058 cites W2160956336 @default.
• W2902873058 cites W2171740948 @default.
• W2902873058 cites W2254462240 @default.
• W2902873058 cites W2434421859 @default.
• W2902873058 cites W2436453945 @default.
• W2902873058 cites W2520707372 @default.
• W2902873058 cites W2520953340 @default.
• W2902873058 cites W2555618208 @default.
• W2902873058 cites W2563100679 @default.
• W2902873058 cites W2609883120 @default.
• W2902873058 cites W2612236014 @default.
• W2902873058 cites W2612702926 @default.
• W2902873058 cites W2751274923 @default.
• W2902873058 cites W2755242352 @default.
• W2902873058 cites W2794739174 @default.
• W2902873058 cites W2798365772 @default.
• W2902873058 cites W2798927139 @default.
• W2902873058 cites W2885093229 @default.
• W2902873058 cites W2886851716 @default.
• W2902873058 cites W2897245365 @default.
• W2902873058 cites W2962867954 @default.
• W2902873058 cites W2963045776 @default.
• W2902873058 cites W2963316641 @default.
• W2902873058 cites W2963420272 @default.
• W2902873058 cites W2963549785 @default.
• W2902873058 cites W2963591054 @default.
• W2902873058 cites W2963636093 @default.
• W2902873058 cites W2964110533 @default.
• W2902873058 cites W2969202876 @default.
• W2902873058 cites W2982763192 @default.
• W2902873058 cites W2998293366 @default.
• W2902873058 cites W3102597069 @default.
• W2902873058 cites W53941081 @default.
• W2902873058 doi "https://doi.org/10.48550/arxiv.1812.00488" @default.
• W2902873058 hasPublicationYear "2018" @default.
• W2902873058 type Work @default.
• W2902873058 sameAs 2902873058 @default.
• W2902873058 citedByCount "4" @default.
• W2902873058 countsByYear W29028730582019 @default.
• W2902873058 countsByYear W29028730582021 @default.
• W2902873058 crossrefType "posted-content" @default.
• W2902873058 hasAuthorship W2902873058A5011794291 @default.
• W2902873058 hasAuthorship W2902873058A5021908609 @default.
• W2902873058 hasAuthorship W2902873058A5027159188 @default.
• W2902873058 hasAuthorship W2902873058A5039387461 @default.
• W2902873058 hasAuthorship W2902873058A5058136382 @default.
• W2902873058 hasAuthorship W2902873058A5075311772 @default.
• W2902873058 hasAuthorship W2902873058A5077470082 @default.
• W2902873058 hasBestOaLocation W29028730581 @default.
• W2902873058 hasConcept C108583219 @default.
• W2902873058 hasConcept C115961682 @default.
• W2902873058 hasConcept C124066611 @default.
• W2902873058 hasConcept C127313418 @default.
• W2902873058 hasConcept C13280743 @default.
• W2902873058 hasConcept C141268832 @default.
• W2902873058 hasConcept C153180895 @default.
• W2902873058 hasConcept C154945302 @default.
• W2902873058 hasConcept C185798385 @default.
• W2902873058 hasConcept C2524010 @default.
• W2902873058 hasConcept C2776799497 @default.
• W2902873058 hasConcept C31972630 @default.
• W2902873058 hasConcept C33923547 @default.
• W2902873058 hasConcept C41008148 @default.
• W2902873058 hasConcept C51399673 @default.

• next