FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952669969> ?p ?o ?g. }

• W2952669969 abstract "We present a new local descriptor for 3D shapes, directly applicable to a wide range of shape analysis problems such as point correspondences, semantic segmentation, affordance prediction, and shape-to-scan matching. The descriptor is produced by a convolutional network that is trained to embed geometrically and semantically similar points close to one another in descriptor space. The network processes surface neighborhoods around points on a shape that are captured at multiple scales by a succession of progressively zoomed out views, taken from carefully selected camera positions. We leverage two extremely large sources of data to train our network. First, since our network processes rendered views in the form of 2D images, we repurpose architectures pre-trained on massive image datasets. Second, we automatically generate a synthetic dense point correspondence dataset by non-rigid alignment of corresponding shape parts in a large collection of segmented 3D models. As a result of these design choices, our network effectively encodes multi-scale local context and fine-grained surface detail. Our network can be trained to produce either category-specific descriptors or more generic descriptors by learning from multiple shape categories. Once trained, at test time, the network extracts local descriptors for shapes without requiring any part segmentation as input. Our method can produce effective local descriptors even for shapes whose category is unknown or different from the ones used while training. We demonstrate through several experiments that our learned local descriptors are more discriminative compared to state of the art alternatives, and are effective in a variety of shape analysis applications." @default.
• W2952669969 created "2019-06-27" @default.
• W2952669969 creator A5003312344 @default.
• W2952669969 creator A5028817790 @default.
• W2952669969 creator A5041004771 @default.
• W2952669969 creator A5057980496 @default.
• W2952669969 creator A5068985412 @default.
• W2952669969 creator A5086893989 @default.
• W2952669969 date "2017-06-14" @default.
• W2952669969 modified "2023-09-27" @default.
• W2952669969 title "Learning Local Shape Descriptors from Part Correspondences With Multi-view Convolutional Networks" @default.
• W2952669969 cites W1493004075 @default.
• W2952669969 cites W1522301498 @default.
• W2952669969 cites W1593151701 @default.
• W2952669969 cites W1686810756 @default.
• W2952669969 cites W1869500417 @default.
• W2952669969 cites W1920022804 @default.
• W2952669969 cites W1922697897 @default.
• W2952669969 cites W1929856797 @default.
• W2952669969 cites W1951806617 @default.
• W2952669969 cites W1964601719 @default.
• W2952669969 cites W1977213563 @default.
• W2952669969 cites W1985907520 @default.
• W2952669969 cites W2010209818 @default.
• W2952669969 cites W2021122545 @default.
• W2952669969 cites W2031760064 @default.
• W2952669969 cites W2036163530 @default.
• W2952669969 cites W2040279394 @default.
• W2952669969 cites W2041306713 @default.
• W2952669969 cites W2042997238 @default.
• W2952669969 cites W2047947369 @default.
• W2952669969 cites W2057175746 @default.
• W2952669969 cites W2073700113 @default.
• W2952669969 cites W2088044395 @default.
• W2952669969 cites W2091791686 @default.
• W2952669969 cites W2094262711 @default.
• W2952669969 cites W2099606917 @default.
• W2952669969 cites W2099791118 @default.
• W2952669969 cites W2106723645 @default.
• W2952669969 cites W2109992539 @default.
• W2952669969 cites W2114779816 @default.
• W2952669969 cites W2117539524 @default.
• W2952669969 cites W2134448913 @default.
• W2952669969 cites W2138621090 @default.
• W2952669969 cites W2142873256 @default.
• W2952669969 cites W2145429668 @default.
• W2952669969 cites W2151636374 @default.
• W2952669969 cites W2157218815 @default.
• W2952669969 cites W2160643963 @default.
• W2952669969 cites W2163605009 @default.
• W2952669969 cites W2171590421 @default.
• W2952669969 cites W2229637417 @default.
• W2952669969 cites W2240571584 @default.
• W2952669969 cites W2254644702 @default.
• W2952669969 cites W2295332248 @default.
• W2952669969 cites W2404723690 @default.
• W2952669969 cites W2518780089 @default.
• W2952669969 cites W2553307952 @default.
• W2952669969 cites W2558460151 @default.
• W2952669969 cites W2565662353 @default.
• W2952669969 cites W2580018057 @default.
• W2952669969 cites W2619105901 @default.
• W2952669969 cites W2949503252 @default.
• W2952669969 cites W2949896259 @default.
• W2952669969 cites W2950094539 @default.
• W2952669969 cites W2950747644 @default.
• W2952669969 cites W2952789225 @default.
• W2952669969 cites W2962865163 @default.
• W2952669969 cites W2963333168 @default.
• W2952669969 cites W5023680 @default.
• W2952669969 cites W2622192882 @default.
• W2952669969 doi "https://doi.org/10.48550/arxiv.1706.04496" @default.
• W2952669969 hasPublicationYear "2017" @default.
• W2952669969 type Work @default.
• W2952669969 sameAs 2952669969 @default.
• W2952669969 citedByCount "1" @default.
• W2952669969 countsByYear W29526699692020 @default.
• W2952669969 crossrefType "posted-content" @default.
• W2952669969 hasAuthorship W2952669969A5003312344 @default.
• W2952669969 hasAuthorship W2952669969A5028817790 @default.
• W2952669969 hasAuthorship W2952669969A5041004771 @default.
• W2952669969 hasAuthorship W2952669969A5057980496 @default.
• W2952669969 hasAuthorship W2952669969A5068985412 @default.
• W2952669969 hasAuthorship W2952669969A5086893989 @default.
• W2952669969 hasBestOaLocation W29526699691 @default.
• W2952669969 hasConcept C105795698 @default.
• W2952669969 hasConcept C112604564 @default.
• W2952669969 hasConcept C115961682 @default.
• W2952669969 hasConcept C153083717 @default.
• W2952669969 hasConcept C153180895 @default.
• W2952669969 hasConcept C154945302 @default.
• W2952669969 hasConcept C165064840 @default.
• W2952669969 hasConcept C166957645 @default.
• W2952669969 hasConcept C199360897 @default.
• W2952669969 hasConcept C205649164 @default.
• W2952669969 hasConcept C2524010 @default.
• W2952669969 hasConcept C2779343474 @default.
• W2952669969 hasConcept C2779662243 @default.
• W2952669969 hasConcept C28719098 @default.
• W2952669969 hasConcept C31972630 @default.

• next