FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385237456> ?p ?o ?g. }

• W4385237456 endingPage "499" @default.
• W4385237456 startingPage "484" @default.
• W4385237456 abstract "In the majority of cases, the paired dataset is not easy to obtain, which makes it difficult to train a supervised point cloud upsampling network directly. Therefore, we propose a novel siamese network architecture for the unsupervised upsampling task, called UPU-SNet. This architecture contains two branches based on hierarchical spatial-aware transformers. Specifically, one branch includes a global-local transformer (GLT) module and a standard reconstruction module for coarse point generation. The other contains a shared GLT module, a transformer shuffle (TranShuffle) module and a shared reconstruction module for dense point generation. For multi-level feature extraction, the GLT module we propose aims to explore feature fusions of global-to-local and local-to-global, respectively, with the aid of the multi-head cross-attention mechanism of the transformers. Then, the TranShuffle module is constructed closely after the GLT module to further optimize and expand the extracted features. Moreover, taking full account of sparse points, coarse points and dense points, we design a joint loss function, so as to support the network to generate denser and more uniform point clouds without using ground-truth. Through extensive experiments, we show how our proposal not only outperforms existing unsupervised methods but also achieves competitive results against previous supervised and self-supervised methods. Also, we presente various surface reconstruction results on both synthetic and real point clouds, and show our network can enable accurate 3D reconstructions." @default.
• W4385237456 created "2023-07-26" @default.
• W4385237456 creator A5003953815 @default.
• W4385237456 creator A5040613149 @default.
• W4385237456 creator A5063351222 @default.
• W4385237456 creator A5089011905 @default.
• W4385237456 date "2023-10-01" @default.
• W4385237456 modified "2023-09-23" @default.
• W4385237456 title "UPU-SNet: Siamese network for unsupervised point cloud upsampling based on spatial-aware transformers" @default.
• W4385237456 cites W1988317275 @default.
• W4385237456 cites W1992642990 @default.
• W4385237456 cites W2025973801 @default.
• W4385237456 cites W2137531922 @default.
• W4385237456 cites W2143668817 @default.
• W4385237456 cites W2154385726 @default.
• W4385237456 cites W2169611956 @default.
• W4385237456 cites W2171590421 @default.
• W4385237456 cites W2460657278 @default.
• W4385237456 cites W2476548250 @default.
• W4385237456 cites W2594519801 @default.
• W4385237456 cites W2796426482 @default.
• W4385237456 cites W2884154111 @default.
• W4385237456 cites W2900862165 @default.
• W4385237456 cites W2963680153 @default.
• W4385237456 cites W2964140013 @default.
• W4385237456 cites W2970633157 @default.
• W4385237456 cites W2997337685 @default.
• W4385237456 cites W3106147826 @default.
• W4385237456 cites W3106699132 @default.
• W4385237456 cites W3113317635 @default.
• W4385237456 cites W3137466219 @default.
• W4385237456 cites W3138516171 @default.
• W4385237456 cites W3151130473 @default.
• W4385237456 cites W3168825659 @default.
• W4385237456 cites W3171007011 @default.
• W4385237456 cites W3175676582 @default.
• W4385237456 cites W3184736166 @default.
• W4385237456 cites W3203898101 @default.
• W4385237456 cites W3207658203 @default.
• W4385237456 cites W4214624153 @default.
• W4385237456 cites W4214755140 @default.
• W4385237456 cites W4221138238 @default.
• W4385237456 cites W4225574139 @default.
• W4385237456 cites W4225690763 @default.
• W4385237456 cites W4226095806 @default.
• W4385237456 cites W4226373316 @default.
• W4385237456 cites W4229450040 @default.
• W4385237456 cites W4282928804 @default.
• W4385237456 cites W4288092002 @default.
• W4385237456 cites W4312571097 @default.
• W4385237456 cites W4312602556 @default.
• W4385237456 cites W4313019631 @default.
• W4385237456 cites W4313056800 @default.
• W4385237456 cites W4313145913 @default.
• W4385237456 cites W4315836328 @default.
• W4385237456 cites W4328027899 @default.
• W4385237456 cites W4386065824 @default.
• W4385237456 cites W4386071863 @default.
• W4385237456 cites W4386075739 @default.
• W4385237456 cites W4386075817 @default.
• W4385237456 cites W4386075872 @default.
• W4385237456 cites W4386076385 @default.
• W4385237456 doi "https://doi.org/10.1016/j.cag.2023.07.037" @default.
• W4385237456 hasPublicationYear "2023" @default.
• W4385237456 type Work @default.
• W4385237456 citedByCount "0" @default.
• W4385237456 crossrefType "journal-article" @default.
• W4385237456 hasAuthorship W4385237456A5003953815 @default.
• W4385237456 hasAuthorship W4385237456A5040613149 @default.
• W4385237456 hasAuthorship W4385237456A5063351222 @default.
• W4385237456 hasAuthorship W4385237456A5089011905 @default.
• W4385237456 hasConcept C110384440 @default.
• W4385237456 hasConcept C115961682 @default.
• W4385237456 hasConcept C121332964 @default.
• W4385237456 hasConcept C131979681 @default.
• W4385237456 hasConcept C134306372 @default.
• W4385237456 hasConcept C153180895 @default.
• W4385237456 hasConcept C154945302 @default.
• W4385237456 hasConcept C165801399 @default.
• W4385237456 hasConcept C31972630 @default.
• W4385237456 hasConcept C33923547 @default.
• W4385237456 hasConcept C41008148 @default.
• W4385237456 hasConcept C62520636 @default.
• W4385237456 hasConcept C66322947 @default.
• W4385237456 hasConcept C73000952 @default.
• W4385237456 hasConceptScore W4385237456C110384440 @default.
• W4385237456 hasConceptScore W4385237456C115961682 @default.
• W4385237456 hasConceptScore W4385237456C121332964 @default.
• W4385237456 hasConceptScore W4385237456C131979681 @default.
• W4385237456 hasConceptScore W4385237456C134306372 @default.
• W4385237456 hasConceptScore W4385237456C153180895 @default.
• W4385237456 hasConceptScore W4385237456C154945302 @default.
• W4385237456 hasConceptScore W4385237456C165801399 @default.
• W4385237456 hasConceptScore W4385237456C31972630 @default.
• W4385237456 hasConceptScore W4385237456C33923547 @default.
• W4385237456 hasConceptScore W4385237456C41008148 @default.
• W4385237456 hasConceptScore W4385237456C62520636 @default.
• W4385237456 hasConceptScore W4385237456C66322947 @default.

• next