FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950454986> ?p ?o ?g. }

• W2950454986 abstract "Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down recursive decomposition and develop the first deep learning model for hierarchical segmentation of 3D shapes, based on recursive neural networks. Starting from a full shape represented as a point cloud, our model performs recursive binary decomposition, where the decomposition network at all nodes in the hierarchy share weights. At each node, a node classifier is trained to determine the type (adjacency or symmetry) and stopping criteria of its decomposition. The features extracted in higher level nodes are recursively propagated to lower level ones. Thus, the meaningful decompositions in higher levels provide strong contextual cues constraining the segmentations in lower levels. Meanwhile, to increase the segmentation accuracy at each node, we enhance the recursive contextual feature with the shape feature extracted for the corresponding part. Our method segments a 3D shape in point cloud into an unfixed number of parts, depending on the shape complexity, showing strong generality and flexibility. It achieves the state-of-the-art performance, both for fine-grained and semantic segmentation, on the public benchmark and a new benchmark of fine-grained segmentation proposed in this work. We also demonstrate its application for fine-grained part refinements in image-to-shape reconstruction." @default.
• W2950454986 created "2019-06-27" @default.
• W2950454986 creator A5000248352 @default.
• W2950454986 creator A5034212855 @default.
• W2950454986 creator A5042268563 @default.
• W2950454986 creator A5050501022 @default.
• W2950454986 creator A5052324354 @default.
• W2950454986 date "2019-03-02" @default.
• W2950454986 modified "2023-09-24" @default.
• W2950454986 title "PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation" @default.
• W2950454986 cites W1423339008 @default.
• W2950454986 cites W1569512051 @default.
• W2950454986 cites W1973414297 @default.
• W2950454986 cites W1975807399 @default.
• W2950454986 cites W1987370452 @default.
• W2950454986 cites W1992971572 @default.
• W2950454986 cites W1994838542 @default.
• W2950454986 cites W2022922662 @default.
• W2950454986 cites W2027069615 @default.
• W2950454986 cites W2030797443 @default.
• W2950454986 cites W2050204708 @default.
• W2950454986 cites W2106210044 @default.
• W2950454986 cites W2106723645 @default.
• W2950454986 cites W2109992539 @default.
• W2950454986 cites W2141411966 @default.
• W2950454986 cites W2151735154 @default.
• W2950454986 cites W2190691619 @default.
• W2950454986 cites W2553307952 @default.
• W2950454986 cites W2556802233 @default.
• W2950454986 cites W2560722161 @default.
• W2950454986 cites W2565662353 @default.
• W2950454986 cites W2580666155 @default.
• W2950454986 cites W2594727217 @default.
• W2950454986 cites W2612843093 @default.
• W2950454986 cites W2769312834 @default.
• W2950454986 cites W2788158258 @default.
• W2950454986 cites W2884948865 @default.
• W2950454986 cites W2902330865 @default.
• W2950454986 cites W2950642167 @default.
• W2950454986 cites W2962780613 @default.
• W2950454986 cites W2962928871 @default.
• W2950454986 cites W2963121255 @default.
• W2950454986 cites W2963182550 @default.
• W2950454986 cites W2963333168 @default.
• W2950454986 cites W2963400238 @default.
• W2950454986 cites W2963517242 @default.
• W2950454986 cites W2964253930 @default.
• W2950454986 cites W3103022131 @default.
• W2950454986 cites W3104141662 @default.
• W2950454986 doi "https://doi.org/10.48550/arxiv.1903.00709" @default.
• W2950454986 hasPublicationYear "2019" @default.
• W2950454986 type Work @default.
• W2950454986 sameAs 2950454986 @default.
• W2950454986 citedByCount "2" @default.
• W2950454986 countsByYear W29504549862019 @default.
• W2950454986 countsByYear W29504549862020 @default.
• W2950454986 crossrefType "posted-content" @default.
• W2950454986 hasAuthorship W2950454986A5000248352 @default.
• W2950454986 hasAuthorship W2950454986A5034212855 @default.
• W2950454986 hasAuthorship W2950454986A5042268563 @default.
• W2950454986 hasAuthorship W2950454986A5050501022 @default.
• W2950454986 hasAuthorship W2950454986A5052324354 @default.
• W2950454986 hasBestOaLocation W29504549861 @default.
• W2950454986 hasConcept C108583219 @default.
• W2950454986 hasConcept C131979681 @default.
• W2950454986 hasConcept C13280743 @default.
• W2950454986 hasConcept C138885662 @default.
• W2950454986 hasConcept C153180895 @default.
• W2950454986 hasConcept C154945302 @default.
• W2950454986 hasConcept C185798385 @default.
• W2950454986 hasConcept C205649164 @default.
• W2950454986 hasConcept C2776401178 @default.
• W2950454986 hasConcept C41008148 @default.
• W2950454986 hasConcept C41895202 @default.
• W2950454986 hasConcept C89600930 @default.
• W2950454986 hasConceptScore W2950454986C108583219 @default.
• W2950454986 hasConceptScore W2950454986C131979681 @default.
• W2950454986 hasConceptScore W2950454986C13280743 @default.
• W2950454986 hasConceptScore W2950454986C138885662 @default.
• W2950454986 hasConceptScore W2950454986C153180895 @default.
• W2950454986 hasConceptScore W2950454986C154945302 @default.
• W2950454986 hasConceptScore W2950454986C185798385 @default.
• W2950454986 hasConceptScore W2950454986C205649164 @default.
• W2950454986 hasConceptScore W2950454986C2776401178 @default.
• W2950454986 hasConceptScore W2950454986C41008148 @default.
• W2950454986 hasConceptScore W2950454986C41895202 @default.
• W2950454986 hasConceptScore W2950454986C89600930 @default.
• W2950454986 hasLocation W29504549861 @default.
• W2950454986 hasOpenAccess W2950454986 @default.
• W2950454986 hasPrimaryLocation W29504549861 @default.
• W2950454986 hasRelatedWork W2773120646 @default.
• W2950454986 hasRelatedWork W2790244305 @default.
• W2950454986 hasRelatedWork W2790662084 @default.
• W2950454986 hasRelatedWork W2948658236 @default.
• W2950454986 hasRelatedWork W3097832520 @default.
• W2950454986 hasRelatedWork W4214536195 @default.
• W2950454986 hasRelatedWork W4220708658 @default.
• W2950454986 hasRelatedWork W4243168368 @default.
• W2950454986 hasRelatedWork W4293211451 @default.
• W2950454986 hasRelatedWork W4295036012 @default.

• next