Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323316098> ?p ?o ?g. }
- W4323316098 endingPage "697" @default.
- W4323316098 startingPage "687" @default.
- W4323316098 abstract "Abstract Sparse view 3D reconstruction has attracted increasing attention with the development of neural implicit 3D representation. Existing methods usually only make use of 2D views, requiring a dense set of input views for accurate 3D reconstruction. In this paper, we show that accurate 3D reconstruction can be achieved by incorporating geometric priors into neural implicit 3D reconstruction. Our method adopts the signed distance function as the 3D representation, and learns a generalizable 3D surface reconstruction model from sparse views. Specifically, we build a more effective and sparse feature volume from the input views by using corresponding depth maps, which can be provided by depth sensors or directly predicted from the input views. We recover better geometric details by imposing both depth and surface normal constraints in addition to the color loss when training the neural implicit 3D representation. Experiments demonstrate that our method both outperforms state-of-the-art approaches, and achieves good generalizability." @default.
- W4323316098 created "2023-03-07" @default.
- W4323316098 creator A5011053891 @default.
- W4323316098 creator A5029588621 @default.
- W4323316098 creator A5039085563 @default.
- W4323316098 creator A5067592804 @default.
- W4323316098 date "2023-03-05" @default.
- W4323316098 modified "2023-09-30" @default.
- W4323316098 title "Neural 3D reconstruction from sparse views using geometric priors" @default.
- W4323316098 cites W1979266466 @default.
- W4323316098 cites W2085905957 @default.
- W4323316098 cites W2108417695 @default.
- W4323316098 cites W2129404737 @default.
- W4323316098 cites W2342277278 @default.
- W4323316098 cites W2471962767 @default.
- W4323316098 cites W2565639579 @default.
- W4323316098 cites W2962793285 @default.
- W4323316098 cites W2963221299 @default.
- W4323316098 cites W2964153986 @default.
- W4323316098 cites W3032653087 @default.
- W4323316098 cites W3034259269 @default.
- W4323316098 cites W3034530552 @default.
- W4323316098 cites W3034968345 @default.
- W4323316098 cites W3100341797 @default.
- W4323316098 cites W3107105757 @default.
- W4323316098 cites W3109154950 @default.
- W4323316098 cites W3154129649 @default.
- W4323316098 cites W3159981575 @default.
- W4323316098 cites W3167090845 @default.
- W4323316098 cites W3172568571 @default.
- W4323316098 cites W3172610252 @default.
- W4323316098 cites W3176368002 @default.
- W4323316098 cites W3177963522 @default.
- W4323316098 cites W3181311114 @default.
- W4323316098 cites W3186630079 @default.
- W4323316098 cites W3193602888 @default.
- W4323316098 cites W3202037070 @default.
- W4323316098 cites W3203570626 @default.
- W4323316098 cites W3203887644 @default.
- W4323316098 cites W3204859697 @default.
- W4323316098 cites W3217184254 @default.
- W4323316098 cites W4200150166 @default.
- W4323316098 cites W4214628039 @default.
- W4323316098 cites W4214651109 @default.
- W4323316098 cites W4214655709 @default.
- W4323316098 cites W4282973887 @default.
- W4323316098 cites W4312280100 @default.
- W4323316098 cites W4312539440 @default.
- W4323316098 cites W4312598811 @default.
- W4323316098 cites W4312679369 @default.
- W4323316098 cites W4312819713 @default.
- W4323316098 cites W4313153331 @default.
- W4323316098 cites W4313154783 @default.
- W4323316098 cites W4313186498 @default.
- W4323316098 doi "https://doi.org/10.1007/s41095-023-0337-5" @default.
- W4323316098 hasPublicationYear "2023" @default.
- W4323316098 type Work @default.
- W4323316098 citedByCount "1" @default.
- W4323316098 countsByYear W43233160982023 @default.
- W4323316098 crossrefType "journal-article" @default.
- W4323316098 hasAuthorship W4323316098A5011053891 @default.
- W4323316098 hasAuthorship W4323316098A5029588621 @default.
- W4323316098 hasAuthorship W4323316098A5039085563 @default.
- W4323316098 hasAuthorship W4323316098A5067592804 @default.
- W4323316098 hasBestOaLocation W43233160981 @default.
- W4323316098 hasConcept C105795698 @default.
- W4323316098 hasConcept C107673813 @default.
- W4323316098 hasConcept C109950114 @default.
- W4323316098 hasConcept C124066611 @default.
- W4323316098 hasConcept C138885662 @default.
- W4323316098 hasConcept C141379421 @default.
- W4323316098 hasConcept C153180895 @default.
- W4323316098 hasConcept C154945302 @default.
- W4323316098 hasConcept C17744445 @default.
- W4323316098 hasConcept C177769412 @default.
- W4323316098 hasConcept C199539241 @default.
- W4323316098 hasConcept C20885615 @default.
- W4323316098 hasConcept C2524010 @default.
- W4323316098 hasConcept C27158222 @default.
- W4323316098 hasConcept C2776359362 @default.
- W4323316098 hasConcept C2776401178 @default.
- W4323316098 hasConcept C2776799497 @default.
- W4323316098 hasConcept C31972630 @default.
- W4323316098 hasConcept C33923547 @default.
- W4323316098 hasConcept C36464697 @default.
- W4323316098 hasConcept C41008148 @default.
- W4323316098 hasConcept C41895202 @default.
- W4323316098 hasConcept C45107383 @default.
- W4323316098 hasConcept C77660652 @default.
- W4323316098 hasConcept C94625758 @default.
- W4323316098 hasConceptScore W4323316098C105795698 @default.
- W4323316098 hasConceptScore W4323316098C107673813 @default.
- W4323316098 hasConceptScore W4323316098C109950114 @default.
- W4323316098 hasConceptScore W4323316098C124066611 @default.
- W4323316098 hasConceptScore W4323316098C138885662 @default.
- W4323316098 hasConceptScore W4323316098C141379421 @default.
- W4323316098 hasConceptScore W4323316098C153180895 @default.
- W4323316098 hasConceptScore W4323316098C154945302 @default.