FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896598970> ?p ?o ?g. }

• W2896598970 endingPage "1800" @default.
• W2896598970 startingPage "1780" @default.
• W2896598970 abstract "The objective of this work is to reconstruct the 3D surfaces of sculptures from one or more images using a view-dependent representation. To this end, we train a network, SiDeNet, to predict the Silhouette and Depth of the surface given a variable number of images; the silhouette is predicted at a different viewpoint from the inputs (e.g. from the side), while the depth is predicted at the viewpoint of the input images. This has three benefits. First, the network learns a representation of shape beyond that of a single viewpoint, as the silhouette forces it to respect the visual hull, and the depth image forces it to predict concavities (which don’t appear on the visual hull). Second, as the network learns about 3D using the proxy tasks of predicting depth and silhouette images, it is not limited by the resolution of the 3D representation. Finally, using a view-dependent representation (e.g. additionally encoding the viewpoint with the input image) improves the network’s generalisability to unseen objects. Additionally, the network is able to handle the input views in a flexible manner. First, it can ingest a different number of views during training and testing, and it is shown that the reconstruction performance improves as additional views are added at test-time. Second, the additional views do not need to be photometrically consistent. The network is trained and evaluated on two synthetic datasets—a realistic sculpture dataset (SketchFab), and ShapeNet. The design of the network is validated by comparing to state of the art methods for a set of tasks. It is shown that (i) passing the input viewpoint (i.e. using a view-dependent representation) improves the network’s generalisability at test time. (ii) Predicting depth/silhouette images allows for higher quality predictions in 2D, as the network is not limited by the chosen latent 3D representation. (iii) On both datasets the method of combining views in a global manner performs better than a local method. Finally, we show that the trained network generalizes to real images, and probe how the network has encoded the latent 3D shape." @default.
• W2896598970 created "2018-10-26" @default.
• W2896598970 creator A5051904433 @default.
• W2896598970 creator A5057678172 @default.
• W2896598970 date "2018-10-22" @default.
• W2896598970 modified "2023-10-16" @default.
• W2896598970 title "Learning to Predict 3D Surfaces of Sculptures from Single and Multiple Views" @default.
• W2896598970 cites W1644641054 @default.
• W2896598970 cites W1893912098 @default.
• W2896598970 cites W1901129140 @default.
• W2896598970 cites W1915485278 @default.
• W2896598970 cites W1927784829 @default.
• W2896598970 cites W1991264156 @default.
• W2896598970 cites W1997396833 @default.
• W2896598970 cites W2006227471 @default.
• W2896598970 cites W2010714106 @default.
• W2896598970 cites W2013599012 @default.
• W2896598970 cites W2020429267 @default.
• W2896598970 cites W2027560260 @default.
• W2896598970 cites W2033819227 @default.
• W2896598970 cites W2035457768 @default.
• W2896598970 cites W2049981393 @default.
• W2896598970 cites W2066090933 @default.
• W2896598970 cites W2117007522 @default.
• W2896598970 cites W2118304946 @default.
• W2896598970 cites W2126683984 @default.
• W2896598970 cites W2142540472 @default.
• W2896598970 cites W2160014001 @default.
• W2896598970 cites W2237250383 @default.
• W2896598970 cites W2259631822 @default.
• W2896598970 cites W2342277278 @default.
• W2896598970 cites W2348664362 @default.
• W2896598970 cites W2495603374 @default.
• W2896598970 cites W2534523274 @default.
• W2896598970 cites W2598591334 @default.
• W2896598970 cites W2604493845 @default.
• W2896598970 cites W2738835886 @default.
• W2896598970 cites W2962731536 @default.
• W2896598970 cites W2963002018 @default.
• W2896598970 cites W2963073614 @default.
• W2896598970 cites W2963641844 @default.
• W2896598970 cites W2963739349 @default.
• W2896598970 cites W2963870144 @default.
• W2896598970 cites W2964053173 @default.
• W2896598970 cites W2964137676 @default.
• W2896598970 doi "https://doi.org/10.1007/s11263-018-1124-0" @default.
• W2896598970 hasPublicationYear "2018" @default.
• W2896598970 type Work @default.
• W2896598970 sameAs 2896598970 @default.
• W2896598970 citedByCount "10" @default.
• W2896598970 countsByYear W28965989702019 @default.
• W2896598970 countsByYear W28965989702020 @default.
• W2896598970 countsByYear W28965989702021 @default.
• W2896598970 countsByYear W28965989702022 @default.
• W2896598970 countsByYear W28965989702023 @default.
• W2896598970 crossrefType "journal-article" @default.
• W2896598970 hasAuthorship W2896598970A5051904433 @default.
• W2896598970 hasAuthorship W2896598970A5057678172 @default.
• W2896598970 hasBestOaLocation W28965989701 @default.
• W2896598970 hasConcept C153180895 @default.
• W2896598970 hasConcept C154945302 @default.
• W2896598970 hasConcept C17744445 @default.
• W2896598970 hasConcept C199539241 @default.
• W2896598970 hasConcept C2776359362 @default.
• W2896598970 hasConcept C2776863239 @default.
• W2896598970 hasConcept C31972630 @default.
• W2896598970 hasConcept C41008148 @default.
• W2896598970 hasConcept C58103923 @default.
• W2896598970 hasConcept C94625758 @default.
• W2896598970 hasConceptScore W2896598970C153180895 @default.
• W2896598970 hasConceptScore W2896598970C154945302 @default.
• W2896598970 hasConceptScore W2896598970C17744445 @default.
• W2896598970 hasConceptScore W2896598970C199539241 @default.
• W2896598970 hasConceptScore W2896598970C2776359362 @default.
• W2896598970 hasConceptScore W2896598970C2776863239 @default.
• W2896598970 hasConceptScore W2896598970C31972630 @default.
• W2896598970 hasConceptScore W2896598970C41008148 @default.
• W2896598970 hasConceptScore W2896598970C58103923 @default.
• W2896598970 hasConceptScore W2896598970C94625758 @default.
• W2896598970 hasFunder F4320334627 @default.
• W2896598970 hasIssue "11-12" @default.
• W2896598970 hasLocation W28965989701 @default.
• W2896598970 hasLocation W28965989702 @default.
• W2896598970 hasOpenAccess W2896598970 @default.
• W2896598970 hasPrimaryLocation W28965989701 @default.
• W2896598970 hasRelatedWork W1792369072 @default.
• W2896598970 hasRelatedWork W1982074361 @default.
• W2896598970 hasRelatedWork W2073683511 @default.
• W2896598970 hasRelatedWork W2095701144 @default.
• W2896598970 hasRelatedWork W2099159136 @default.
• W2896598970 hasRelatedWork W2112695225 @default.
• W2896598970 hasRelatedWork W2121860908 @default.
• W2896598970 hasRelatedWork W2144343716 @default.
• W2896598970 hasRelatedWork W2168039919 @default.
• W2896598970 hasRelatedWork W2168333068 @default.
• W2896598970 hasVolume "127" @default.
• W2896598970 isParatext "false" @default.
• W2896598970 isRetracted "false" @default.

• next