Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204691786> ?p ?o ?g. }
- W3204691786 abstract "Accurate camera pose estimation or global camera re-localization is a core component in Structure-from-Motion (SfM) and SLAM systems. Given pair-wise relative camera poses, pose-graph optimization (PGO) involves solving for an optimized set of globally-consistent absolute camera poses. In this work, we propose a novel PGO scheme fueled by graph neural networks (GNN), namely PoGO-Net, to conduct the absolute camera pose regression leveraging multiple rotation averaging (MRA). Specifically, PoGO-Net takes a noisy view-graph as the input, where the nodes and edges are designed to encode the geometric constraints and local graph consistency. Besides, we address the outlier edge removal by exploiting an implicit edge-dropping scheme where the noisy or corrupted edges are effectively filtered out with parameterized networks. Furthermore, we introduce a joint loss function embedding MRA formulation such that the robust inference is capable of achieving real-time performances even for large-scale scenes. Our proposed network is trained end-to-end on public benchmarks, outperforming state-of-the-art approaches in extensive experiments that demonstrate the efficiency and robustness of our proposed network." @default.
- W3204691786 created "2021-10-11" @default.
- W3204691786 creator A5032748496 @default.
- W3204691786 creator A5061469520 @default.
- W3204691786 date "2021-10-01" @default.
- W3204691786 modified "2023-10-01" @default.
- W3204691786 title "PoGO-Net: Pose Graph Optimization with Graph Neural Networks" @default.
- W3204691786 cites W1536617987 @default.
- W3204691786 cites W1579664581 @default.
- W3204691786 cites W1989476314 @default.
- W3204691786 cites W1993228150 @default.
- W3204691786 cites W2001790138 @default.
- W3204691786 cites W2007806707 @default.
- W3204691786 cites W2013472030 @default.
- W3204691786 cites W2084613528 @default.
- W3204691786 cites W2085261163 @default.
- W3204691786 cites W2105303354 @default.
- W3204691786 cites W2105413810 @default.
- W3204691786 cites W2109757902 @default.
- W3204691786 cites W2111073598 @default.
- W3204691786 cites W2116341502 @default.
- W3204691786 cites W2133192850 @default.
- W3204691786 cites W2150066425 @default.
- W3204691786 cites W2151290401 @default.
- W3204691786 cites W2160335633 @default.
- W3204691786 cites W2171244244 @default.
- W3204691786 cites W2194775991 @default.
- W3204691786 cites W2200124539 @default.
- W3204691786 cites W2520592772 @default.
- W3204691786 cites W2584731199 @default.
- W3204691786 cites W2594519801 @default.
- W3204691786 cites W2605111497 @default.
- W3204691786 cites W2749379418 @default.
- W3204691786 cites W2795645133 @default.
- W3204691786 cites W2895192073 @default.
- W3204691786 cites W2922243907 @default.
- W3204691786 cites W2937063044 @default.
- W3204691786 cites W2962799344 @default.
- W3204691786 cites W2962895018 @default.
- W3204691786 cites W2963537367 @default.
- W3204691786 cites W2964222388 @default.
- W3204691786 cites W2978166726 @default.
- W3204691786 cites W2983230029 @default.
- W3204691786 cites W2987570663 @default.
- W3204691786 cites W3021282624 @default.
- W3204691786 cites W3035211723 @default.
- W3204691786 cites W3035272603 @default.
- W3204691786 cites W3035397262 @default.
- W3204691786 cites W3096709480 @default.
- W3204691786 cites W3103125695 @default.
- W3204691786 cites W3103648783 @default.
- W3204691786 cites W3110204544 @default.
- W3204691786 cites W3116239416 @default.
- W3204691786 cites W4246559506 @default.
- W3204691786 cites W4247250903 @default.
- W3204691786 cites W4248598408 @default.
- W3204691786 doi "https://doi.org/10.1109/iccv48922.2021.00584" @default.
- W3204691786 hasPublicationYear "2021" @default.
- W3204691786 type Work @default.
- W3204691786 sameAs 3204691786 @default.
- W3204691786 citedByCount "6" @default.
- W3204691786 countsByYear W32046917862022 @default.
- W3204691786 countsByYear W32046917862023 @default.
- W3204691786 crossrefType "proceedings-article" @default.
- W3204691786 hasAuthorship W3204691786A5032748496 @default.
- W3204691786 hasAuthorship W3204691786A5061469520 @default.
- W3204691786 hasConcept C104317684 @default.
- W3204691786 hasConcept C132525143 @default.
- W3204691786 hasConcept C153180895 @default.
- W3204691786 hasConcept C154945302 @default.
- W3204691786 hasConcept C185592680 @default.
- W3204691786 hasConcept C31972630 @default.
- W3204691786 hasConcept C41008148 @default.
- W3204691786 hasConcept C41608201 @default.
- W3204691786 hasConcept C52102323 @default.
- W3204691786 hasConcept C55493867 @default.
- W3204691786 hasConcept C63479239 @default.
- W3204691786 hasConcept C66746571 @default.
- W3204691786 hasConcept C75564084 @default.
- W3204691786 hasConcept C80444323 @default.
- W3204691786 hasConceptScore W3204691786C104317684 @default.
- W3204691786 hasConceptScore W3204691786C132525143 @default.
- W3204691786 hasConceptScore W3204691786C153180895 @default.
- W3204691786 hasConceptScore W3204691786C154945302 @default.
- W3204691786 hasConceptScore W3204691786C185592680 @default.
- W3204691786 hasConceptScore W3204691786C31972630 @default.
- W3204691786 hasConceptScore W3204691786C41008148 @default.
- W3204691786 hasConceptScore W3204691786C41608201 @default.
- W3204691786 hasConceptScore W3204691786C52102323 @default.
- W3204691786 hasConceptScore W3204691786C55493867 @default.
- W3204691786 hasConceptScore W3204691786C63479239 @default.
- W3204691786 hasConceptScore W3204691786C66746571 @default.
- W3204691786 hasConceptScore W3204691786C75564084 @default.
- W3204691786 hasConceptScore W3204691786C80444323 @default.
- W3204691786 hasFunder F4320306076 @default.
- W3204691786 hasLocation W32046917861 @default.
- W3204691786 hasOpenAccess W3204691786 @default.
- W3204691786 hasPrimaryLocation W32046917861 @default.
- W3204691786 hasRelatedWork W1549863447 @default.
- W3204691786 hasRelatedWork W2035976912 @default.