FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198513618> ?p ?o ?g. }

• W3198513618 abstract "Recovering the 3D structure of an object from a single image is a challenging task due to its ill-posed nature. One approach is to utilize the plentiful photos of the same object category to learn a strong 3D shape prior for the object. This approach has successfully been demonstrated by a recent work of Wu et al. (2020), which obtained impressive 3D reconstruction networks with unsupervised learning. However, their algorithm is only applicable to symmetric objects. In this paper, we eliminate the symmetry requirement with a novel unsupervised algorithm that can learn a 3D reconstruction network from a multi-image dataset. Our algorithm is more general and covers the symmetry-required scenario as a special case. Besides, we employ a novel albedo loss that improves the reconstructed details and realisticity. Our method surpasses the previous work in both quality and robustness, as shown in experiments on datasets of various structures, including single-view, multiview, image-collection, and video sets. Code is available at: https://github.com/VinAIResearch/LeMul." @default.
• W3198513618 created "2021-09-13" @default.
• W3198513618 creator A5022051775 @default.
• W3198513618 creator A5038957718 @default.
• W3198513618 creator A5045616447 @default.
• W3198513618 creator A5087479883 @default.
• W3198513618 date "2021-10-01" @default.
• W3198513618 modified "2023-10-03" @default.
• W3198513618 title "Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images" @default.
• W3198513618 cites W1834627138 @default.
• W3198513618 cites W1905829557 @default.
• W3198513618 cites W19301072 @default.
• W3198513618 cites W1977295328 @default.
• W3198513618 cites W2008706659 @default.
• W3198513618 cites W2019464758 @default.
• W3198513618 cites W2067164770 @default.
• W3198513618 cites W2083880226 @default.
• W3198513618 cites W2097307110 @default.
• W3198513618 cites W2097365005 @default.
• W3198513618 cites W2107037917 @default.
• W3198513618 cites W2118304946 @default.
• W3198513618 cites W2122585444 @default.
• W3198513618 cites W2128597272 @default.
• W3198513618 cites W2129201358 @default.
• W3198513618 cites W2147334734 @default.
• W3198513618 cites W2152826865 @default.
• W3198513618 cites W2163998463 @default.
• W3198513618 cites W2172803778 @default.
• W3198513618 cites W2237250383 @default.
• W3198513618 cites W2296659146 @default.
• W3198513618 cites W2519131448 @default.
• W3198513618 cites W2561074213 @default.
• W3198513618 cites W2584229793 @default.
• W3198513618 cites W2609883120 @default.
• W3198513618 cites W2796822548 @default.
• W3198513618 cites W2799123546 @default.
• W3198513618 cites W2897765997 @default.
• W3198513618 cites W2962811204 @default.
• W3198513618 cites W2963409406 @default.
• W3198513618 cites W2963488291 @default.
• W3198513618 cites W2963527086 @default.
• W3198513618 cites W2963641844 @default.
• W3198513618 cites W2964014680 @default.
• W3198513618 cites W2964014798 @default.
• W3198513618 cites W2964093990 @default.
• W3198513618 cites W2978956737 @default.
• W3198513618 cites W2979577579 @default.
• W3198513618 cites W3035191304 @default.
• W3198513618 cites W3035523051 @default.
• W3198513618 cites W4256017923 @default.
• W3198513618 doi "https://doi.org/10.1109/iccv48922.2021.01237" @default.
• W3198513618 hasPublicationYear "2021" @default.
• W3198513618 type Work @default.
• W3198513618 sameAs 3198513618 @default.
• W3198513618 citedByCount "4" @default.
• W3198513618 countsByYear W31985136182022 @default.
• W3198513618 countsByYear W31985136182023 @default.
• W3198513618 crossrefType "proceedings-article" @default.
• W3198513618 hasAuthorship W3198513618A5022051775 @default.
• W3198513618 hasAuthorship W3198513618A5038957718 @default.
• W3198513618 hasAuthorship W3198513618A5045616447 @default.
• W3198513618 hasAuthorship W3198513618A5087479883 @default.
• W3198513618 hasBestOaLocation W31985136182 @default.
• W3198513618 hasConcept C104317684 @default.
• W3198513618 hasConcept C108583219 @default.
• W3198513618 hasConcept C115961682 @default.
• W3198513618 hasConcept C141379421 @default.
• W3198513618 hasConcept C153180895 @default.
• W3198513618 hasConcept C154945302 @default.
• W3198513618 hasConcept C177264268 @default.
• W3198513618 hasConcept C185592680 @default.
• W3198513618 hasConcept C199360897 @default.
• W3198513618 hasConcept C2776760102 @default.
• W3198513618 hasConcept C2781238097 @default.
• W3198513618 hasConcept C31972630 @default.
• W3198513618 hasConcept C41008148 @default.
• W3198513618 hasConcept C55493867 @default.
• W3198513618 hasConcept C63479239 @default.
• W3198513618 hasConcept C8038995 @default.
• W3198513618 hasConceptScore W3198513618C104317684 @default.
• W3198513618 hasConceptScore W3198513618C108583219 @default.
• W3198513618 hasConceptScore W3198513618C115961682 @default.
• W3198513618 hasConceptScore W3198513618C141379421 @default.
• W3198513618 hasConceptScore W3198513618C153180895 @default.
• W3198513618 hasConceptScore W3198513618C154945302 @default.
• W3198513618 hasConceptScore W3198513618C177264268 @default.
• W3198513618 hasConceptScore W3198513618C185592680 @default.
• W3198513618 hasConceptScore W3198513618C199360897 @default.
• W3198513618 hasConceptScore W3198513618C2776760102 @default.
• W3198513618 hasConceptScore W3198513618C2781238097 @default.
• W3198513618 hasConceptScore W3198513618C31972630 @default.
• W3198513618 hasConceptScore W3198513618C41008148 @default.
• W3198513618 hasConceptScore W3198513618C55493867 @default.
• W3198513618 hasConceptScore W3198513618C63479239 @default.
• W3198513618 hasConceptScore W3198513618C8038995 @default.
• W3198513618 hasLocation W31985136181 @default.
• W3198513618 hasLocation W31985136182 @default.
• W3198513618 hasOpenAccess W3198513618 @default.
• W3198513618 hasPrimaryLocation W31985136181 @default.
• W3198513618 hasRelatedWork W1837097281 @default.

• next