FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100398946> ?p ?o ?g. }

• W3100398946 startingPage "65" @default.
• W3100398946 abstract "Modeling and rendering of dynamic scenes is challenging, as natural scenes often contain complex phenomena such as thin structures, evolving topology, translucency, scattering, occlusion, and biological motion. Mesh-based reconstruction and tracking often fail in these cases, and other approaches (e.g., light field video) typically rely on constrained viewing conditions, which limit interactivity. We circumvent these difficulties by presenting a learning-based approach to representing dynamic objects inspired by the integral projection model used in tomographic imaging. The approach is supervised directly from 2D images in a multi-view capture setting and does not require explicit reconstruction or tracking of the object. Our method has two primary components: an encoder-decoder network that transforms input images into a 3D volume representation, and a differentiable ray-marching operation that enables end-to-end training. By virtue of its 3D representation, our construction extrapolates better to novel viewpoints compared to screen-space rendering techniques. The encoder-decoder architecture learns a latent representation of a dynamic scene that enables us to produce novel content sequences not seen during training. To overcome memory limitations of voxel-based representations, we learn a dynamic irregular grid structure implemented with a warp field during ray-marching. This structure greatly improves the apparent resolution and reduces grid-like artifacts and jagged motion. Finally, we demonstrate how to incorporate surface-based representations into our volumetric-learning framework for applications where the highest resolution is required, using facial performance capture as a case in point." @default.
• W3100398946 created "2020-11-23" @default.
• W3100398946 creator A5017813263 @default.
• W3100398946 creator A5043754746 @default.
• W3100398946 creator A5060280374 @default.
• W3100398946 creator A5068089881 @default.
• W3100398946 creator A5073074308 @default.
• W3100398946 creator A5082178717 @default.
• W3100398946 date "2019-07-12" @default.
• W3100398946 modified "2023-10-18" @default.
• W3100398946 title "Neural volumes: learning dynamic renderable volumes from images" @default.
• W3100398946 cites W1938204631 @default.
• W3100398946 cites W1993962870 @default.
• W3100398946 cites W2044618760 @default.
• W3100398946 cites W2054725989 @default.
• W3100398946 cites W2066763472 @default.
• W3100398946 cites W2069997605 @default.
• W3100398946 cites W2071906076 @default.
• W3100398946 cites W2075402943 @default.
• W3100398946 cites W2076246983 @default.
• W3100398946 cites W2104974755 @default.
• W3100398946 cites W2112340554 @default.
• W3100398946 cites W2116546169 @default.
• W3100398946 cites W2118791399 @default.
• W3100398946 cites W2119231080 @default.
• W3100398946 cites W2121299550 @default.
• W3100398946 cites W2129404737 @default.
• W3100398946 cites W2132139399 @default.
• W3100398946 cites W2156116778 @default.
• W3100398946 cites W2167335287 @default.
• W3100398946 cites W2167696327 @default.
• W3100398946 cites W2168545424 @default.
• W3100398946 cites W2171056981 @default.
• W3100398946 cites W2174133987 @default.
• W3100398946 cites W2238402354 @default.
• W3100398946 cites W2257063750 @default.
• W3100398946 cites W2325034626 @default.
• W3100398946 cites W2338968644 @default.
• W3100398946 cites W2471962767 @default.
• W3100398946 cites W2472319119 @default.
• W3100398946 cites W2519683295 @default.
• W3100398946 cites W2551052086 @default.
• W3100398946 cites W2556802233 @default.
• W3100398946 cites W2608696995 @default.
• W3100398946 cites W2753738274 @default.
• W3100398946 cites W2758175304 @default.
• W3100398946 cites W2772927275 @default.
• W3100398946 cites W2798856139 @default.
• W3100398946 cites W2806833697 @default.
• W3100398946 cites W2808532172 @default.
• W3100398946 cites W2811426698 @default.
• W3100398946 cites W2886748926 @default.
• W3100398946 cites W2896892492 @default.
• W3100398946 cites W2901584762 @default.
• W3100398946 cites W2901982540 @default.
• W3100398946 cites W2903200123 @default.
• W3100398946 cites W2950477723 @default.
• W3100398946 cites W2951004968 @default.
• W3100398946 cites W2962760235 @default.
• W3100398946 cites W2962912205 @default.
• W3100398946 cites W2963073614 @default.
• W3100398946 cites W2963557767 @default.
• W3100398946 cites W2963564867 @default.
• W3100398946 cites W2963739349 @default.
• W3100398946 cites W2964013315 @default.
• W3100398946 cites W2964121744 @default.
• W3100398946 cites W2968257580 @default.
• W3100398946 cites W3159981575 @default.
• W3100398946 cites W603908379 @default.
• W3100398946 cites W83557104 @default.
• W3100398946 cites W2337062560 @default.
• W3100398946 hasPublicationYear "2019" @default.
• W3100398946 type Work @default.
• W3100398946 sameAs 3100398946 @default.
• W3100398946 citedByCount "130" @default.
• W3100398946 countsByYear W31003989462019 @default.
• W3100398946 countsByYear W31003989462020 @default.
• W3100398946 countsByYear W31003989462021 @default.
• W3100398946 countsByYear W31003989462022 @default.
• W3100398946 crossrefType "journal-article" @default.
• W3100398946 hasAuthorship W3100398946A5017813263 @default.
• W3100398946 hasAuthorship W3100398946A5043754746 @default.
• W3100398946 hasAuthorship W3100398946A5060280374 @default.
• W3100398946 hasAuthorship W3100398946A5068089881 @default.
• W3100398946 hasAuthorship W3100398946A5073074308 @default.
• W3100398946 hasAuthorship W3100398946A5082178717 @default.
• W3100398946 hasBestOaLocation W31003989461 @default.
• W3100398946 hasConcept C154945302 @default.
• W3100398946 hasConcept C187691185 @default.
• W3100398946 hasConcept C205711294 @default.
• W3100398946 hasConcept C2524010 @default.
• W3100398946 hasConcept C31972630 @default.
• W3100398946 hasConcept C33923547 @default.
• W3100398946 hasConcept C41008148 @default.
• W3100398946 hasConceptScore W3100398946C154945302 @default.
• W3100398946 hasConceptScore W3100398946C187691185 @default.
• W3100398946 hasConceptScore W3100398946C205711294 @default.
• W3100398946 hasConceptScore W3100398946C2524010 @default.
• W3100398946 hasConceptScore W3100398946C31972630 @default.

• next