Matches in SemOpenAlex for { <https://semopenalex.org/work/W2953808575> ?p ?o ?g. }
- W2953808575 abstract "The growing availability of commodity RGB-D cameras has boosted the applications in the field of scene understanding. However, as a fundamental scene understanding task, surface normal estimation from RGB-D data lacks thorough investigation. In this paper, a hierarchical fusion network with adaptive feature re-weighting is proposed for surface normal estimation from a single RGB-D image. Specifically, the features from color image and depth are successively integrated at multiple scales to ensure global surface smoothness while preserving visually salient details. Meanwhile, the depth features are re-weighted with a confidence map estimated from depth before merging into the color branch to avoid artifacts caused by input depth corruption. Additionally, a hybrid multi-scale loss function is designed to learn accurate normal estimation given noisy ground-truth dataset. Extensive experimental results validate the effectiveness of the fusion strategy and the loss design, outperforming state-of-the-art normal estimation schemes." @default.
- W2953808575 created "2019-07-12" @default.
- W2953808575 creator A5013109703 @default.
- W2953808575 creator A5026250850 @default.
- W2953808575 creator A5048379858 @default.
- W2953808575 creator A5064860911 @default.
- W2953808575 creator A5071393578 @default.
- W2953808575 creator A5085478294 @default.
- W2953808575 creator A5088290384 @default.
- W2953808575 date "2019-04-06" @default.
- W2953808575 modified "2023-09-23" @default.
- W2953808575 title "Deep Surface Normal Estimation with Hierarchical RGB-D Fusion" @default.
- W2953808575 cites W125693051 @default.
- W2953808575 cites W1565402342 @default.
- W2953808575 cites W1568788419 @default.
- W2953808575 cites W1899309388 @default.
- W2953808575 cites W1903029394 @default.
- W2953808575 cites W1905829557 @default.
- W2953808575 cites W1938204631 @default.
- W2953808575 cites W2021191215 @default.
- W2953808575 cites W2099940712 @default.
- W2953808575 cites W2136154655 @default.
- W2953808575 cites W2146814781 @default.
- W2953808575 cites W2550402137 @default.
- W2953808575 cites W2563100679 @default.
- W2953808575 cites W2594519801 @default.
- W2953808575 cites W2609822318 @default.
- W2953808575 cites W2612236014 @default.
- W2953808575 cites W2612702926 @default.
- W2953808575 cites W2755286543 @default.
- W2953808575 cites W2788158258 @default.
- W2953808575 cites W2789616359 @default.
- W2953808575 cites W2794739174 @default.
- W2953808575 cites W2798872691 @default.
- W2953808575 cites W2798927139 @default.
- W2953808575 cites W2886291332 @default.
- W2953808575 cites W2950493473 @default.
- W2953808575 cites W2962762892 @default.
- W2953808575 cites W2962809185 @default.
- W2953808575 cites W2963197375 @default.
- W2953808575 cites W2963896186 @default.
- W2953808575 cites W2964062501 @default.
- W2953808575 cites W2964204553 @default.
- W2953808575 cites W2964339842 @default.
- W2953808575 cites W305753977 @default.
- W2953808575 cites W53941081 @default.
- W2953808575 doi "https://doi.org/10.48550/arxiv.1904.03405" @default.
- W2953808575 hasPublicationYear "2019" @default.
- W2953808575 type Work @default.
- W2953808575 sameAs 2953808575 @default.
- W2953808575 citedByCount "2" @default.
- W2953808575 countsByYear W29538085752019 @default.
- W2953808575 countsByYear W29538085752020 @default.
- W2953808575 crossrefType "posted-content" @default.
- W2953808575 hasAuthorship W2953808575A5013109703 @default.
- W2953808575 hasAuthorship W2953808575A5026250850 @default.
- W2953808575 hasAuthorship W2953808575A5048379858 @default.
- W2953808575 hasAuthorship W2953808575A5064860911 @default.
- W2953808575 hasAuthorship W2953808575A5071393578 @default.
- W2953808575 hasAuthorship W2953808575A5085478294 @default.
- W2953808575 hasAuthorship W2953808575A5088290384 @default.
- W2953808575 hasBestOaLocation W29538085751 @default.
- W2953808575 hasConcept C126838900 @default.
- W2953808575 hasConcept C138885662 @default.
- W2953808575 hasConcept C146849305 @default.
- W2953808575 hasConcept C153180895 @default.
- W2953808575 hasConcept C154945302 @default.
- W2953808575 hasConcept C183115368 @default.
- W2953808575 hasConcept C2524010 @default.
- W2953808575 hasConcept C2776401178 @default.
- W2953808575 hasConcept C2776799497 @default.
- W2953808575 hasConcept C2780719617 @default.
- W2953808575 hasConcept C31972630 @default.
- W2953808575 hasConcept C33923547 @default.
- W2953808575 hasConcept C41008148 @default.
- W2953808575 hasConcept C41895202 @default.
- W2953808575 hasConcept C71924100 @default.
- W2953808575 hasConcept C82990744 @default.
- W2953808575 hasConceptScore W2953808575C126838900 @default.
- W2953808575 hasConceptScore W2953808575C138885662 @default.
- W2953808575 hasConceptScore W2953808575C146849305 @default.
- W2953808575 hasConceptScore W2953808575C153180895 @default.
- W2953808575 hasConceptScore W2953808575C154945302 @default.
- W2953808575 hasConceptScore W2953808575C183115368 @default.
- W2953808575 hasConceptScore W2953808575C2524010 @default.
- W2953808575 hasConceptScore W2953808575C2776401178 @default.
- W2953808575 hasConceptScore W2953808575C2776799497 @default.
- W2953808575 hasConceptScore W2953808575C2780719617 @default.
- W2953808575 hasConceptScore W2953808575C31972630 @default.
- W2953808575 hasConceptScore W2953808575C33923547 @default.
- W2953808575 hasConceptScore W2953808575C41008148 @default.
- W2953808575 hasConceptScore W2953808575C41895202 @default.
- W2953808575 hasConceptScore W2953808575C71924100 @default.
- W2953808575 hasConceptScore W2953808575C82990744 @default.
- W2953808575 hasLocation W29538085751 @default.
- W2953808575 hasOpenAccess W2953808575 @default.
- W2953808575 hasPrimaryLocation W29538085751 @default.
- W2953808575 hasRelatedWork W1164955640 @default.
- W2953808575 hasRelatedWork W2030712947 @default.
- W2953808575 hasRelatedWork W2056979260 @default.