Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310922357> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4310922357 abstract "Neural Radiance Fields (NeRFs) encode the radiance in a scene parameterized by the scene's plenoptic function. This is achieved by using an MLP together with a mapping to a higher-dimensional space, and has been proven to capture scenes with a great level of detail. Naturally, the same parameterization can be used to encode additional properties of the scene, beyond just its radiance. A particularly interesting property in this regard is the semantic decomposition of the scene. We introduce a novel technique for semantic soft decomposition of neural radiance fields (named SSDNeRF) which jointly encodes semantic signals in combination with radiance signals of a scene. Our approach provides a soft decomposition of the scene into semantic parts, enabling us to correctly encode multiple semantic classes blending along the same direction -- an impossible feat for existing methods. Not only does this lead to a detailed, 3D semantic representation of the scene, but we also show that the regularizing effects of the MLP used for encoding help to improve the semantic representation. We show state-of-the-art segmentation and reconstruction results on a dataset of common objects and demonstrate how the proposed approach can be applied for high quality temporally consistent video editing and re-compositing on a dataset of casually captured selfie videos." @default.
- W4310922357 created "2022-12-21" @default.
- W4310922357 creator A5008033744 @default.
- W4310922357 creator A5016046446 @default.
- W4310922357 creator A5020640739 @default.
- W4310922357 creator A5029086954 @default.
- W4310922357 creator A5051363890 @default.
- W4310922357 creator A5061712514 @default.
- W4310922357 creator A5071098396 @default.
- W4310922357 date "2022-12-06" @default.
- W4310922357 modified "2023-10-15" @default.
- W4310922357 title "SSDNeRF: Semantic Soft Decomposition of Neural Radiance Fields" @default.
- W4310922357 doi "https://doi.org/10.48550/arxiv.2212.03406" @default.
- W4310922357 hasPublicationYear "2022" @default.
- W4310922357 type Work @default.
- W4310922357 citedByCount "0" @default.
- W4310922357 crossrefType "posted-content" @default.
- W4310922357 hasAuthorship W4310922357A5008033744 @default.
- W4310922357 hasAuthorship W4310922357A5016046446 @default.
- W4310922357 hasAuthorship W4310922357A5020640739 @default.
- W4310922357 hasAuthorship W4310922357A5029086954 @default.
- W4310922357 hasAuthorship W4310922357A5051363890 @default.
- W4310922357 hasAuthorship W4310922357A5061712514 @default.
- W4310922357 hasAuthorship W4310922357A5071098396 @default.
- W4310922357 hasBestOaLocation W43109223571 @default.
- W4310922357 hasConcept C104317684 @default.
- W4310922357 hasConcept C115961682 @default.
- W4310922357 hasConcept C129315195 @default.
- W4310922357 hasConcept C154945302 @default.
- W4310922357 hasConcept C17744445 @default.
- W4310922357 hasConcept C185592680 @default.
- W4310922357 hasConcept C199539241 @default.
- W4310922357 hasConcept C205649164 @default.
- W4310922357 hasConcept C23690007 @default.
- W4310922357 hasConcept C2776359362 @default.
- W4310922357 hasConcept C31972630 @default.
- W4310922357 hasConcept C41008148 @default.
- W4310922357 hasConcept C55493867 @default.
- W4310922357 hasConcept C62649853 @default.
- W4310922357 hasConcept C66746571 @default.
- W4310922357 hasConcept C89600930 @default.
- W4310922357 hasConcept C94625758 @default.
- W4310922357 hasConceptScore W4310922357C104317684 @default.
- W4310922357 hasConceptScore W4310922357C115961682 @default.
- W4310922357 hasConceptScore W4310922357C129315195 @default.
- W4310922357 hasConceptScore W4310922357C154945302 @default.
- W4310922357 hasConceptScore W4310922357C17744445 @default.
- W4310922357 hasConceptScore W4310922357C185592680 @default.
- W4310922357 hasConceptScore W4310922357C199539241 @default.
- W4310922357 hasConceptScore W4310922357C205649164 @default.
- W4310922357 hasConceptScore W4310922357C23690007 @default.
- W4310922357 hasConceptScore W4310922357C2776359362 @default.
- W4310922357 hasConceptScore W4310922357C31972630 @default.
- W4310922357 hasConceptScore W4310922357C41008148 @default.
- W4310922357 hasConceptScore W4310922357C55493867 @default.
- W4310922357 hasConceptScore W4310922357C62649853 @default.
- W4310922357 hasConceptScore W4310922357C66746571 @default.
- W4310922357 hasConceptScore W4310922357C89600930 @default.
- W4310922357 hasConceptScore W4310922357C94625758 @default.
- W4310922357 hasLocation W43109223571 @default.
- W4310922357 hasLocation W43109223572 @default.
- W4310922357 hasOpenAccess W4310922357 @default.
- W4310922357 hasPrimaryLocation W43109223571 @default.
- W4310922357 hasRelatedWork W2043512367 @default.
- W4310922357 hasRelatedWork W2052474806 @default.
- W4310922357 hasRelatedWork W2098628853 @default.
- W4310922357 hasRelatedWork W2363688420 @default.
- W4310922357 hasRelatedWork W2392142157 @default.
- W4310922357 hasRelatedWork W2605318953 @default.
- W4310922357 hasRelatedWork W2896728493 @default.
- W4310922357 hasRelatedWork W4242350840 @default.
- W4310922357 hasRelatedWork W4321518006 @default.
- W4310922357 hasRelatedWork W775788538 @default.
- W4310922357 isParatext "false" @default.
- W4310922357 isRetracted "false" @default.
- W4310922357 workType "article" @default.