Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386880855> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4386880855 endingPage "11" @default.
- W4386880855 startingPage "1" @default.
- W4386880855 abstract "With the advancement of virtual reality and 3D game technology, the demand for high-quality 3D indoor scene generation has surged. Addressing this need, this paper presents a method leveraging a VAE-GAN-based framework to conquer two primary challenges in 3D scene representation and deep generative networks. First, we introduce a matrix representation to encode fine-grained object attributes, alongside a complete graph to implicitly capture object spatial relations—effectively encapsulating both local and global scene structures. Second, we devise a unique generative framework based on VAE-GAN and the Bayesian optimization. This framework learns a Gaussian distribution of encoded object attributes through a VAE-GAN network, allowing for sampling and decoding of the distribution to generate new object attributes. Subsequently, a U-Net is employed to learn spatial relations between objects. Lastly, the Bayesian optimization module amalgamates the generated object attributes, spatial relations, and priors learned from data, conducting global optimization to generate a logical scene layout. Experimental results on a large-scale 3D indoor scene dataset substantiate that our method effectively learns inter-object relations and generates diverse and plausible indoor scenes. Comparative experiments and user studies further validate that our method surpasses the current state-of-the-art techniques in indoor scene generation and is comparable to real training scenes." @default.
- W4386880855 created "2023-09-21" @default.
- W4386880855 creator A5065155774 @default.
- W4386880855 creator A5082323031 @default.
- W4386880855 date "2023-09-20" @default.
- W4386880855 modified "2023-09-27" @default.
- W4386880855 title "Deep Generative Modeling Based on VAE-GAN for 3D Indoor Scene Synthesis" @default.
- W4386880855 cites W1644641054 @default.
- W4386880855 cites W1989191365 @default.
- W4386880855 cites W2077263423 @default.
- W4386880855 cites W2108598243 @default.
- W4386880855 cites W2162559028 @default.
- W4386880855 cites W2237250383 @default.
- W4386880855 cites W2495603374 @default.
- W4386880855 cites W2509413994 @default.
- W4386880855 cites W2557269700 @default.
- W4386880855 cites W2557465155 @default.
- W4386880855 cites W2560609797 @default.
- W4386880855 cites W2606840594 @default.
- W4386880855 cites W2609754928 @default.
- W4386880855 cites W2612843093 @default.
- W4386880855 cites W2728326942 @default.
- W4386880855 cites W2810181048 @default.
- W4386880855 cites W2960202457 @default.
- W4386880855 cites W2962731536 @default.
- W4386880855 cites W2962928871 @default.
- W4386880855 cites W2963021451 @default.
- W4386880855 cites W2963530975 @default.
- W4386880855 cites W2963601843 @default.
- W4386880855 cites W2964334375 @default.
- W4386880855 cites W3006223838 @default.
- W4386880855 cites W3016025127 @default.
- W4386880855 cites W3096831136 @default.
- W4386880855 cites W3198766663 @default.
- W4386880855 cites W4214625308 @default.
- W4386880855 cites W4297598254 @default.
- W4386880855 doi "https://doi.org/10.1155/2023/3368647" @default.
- W4386880855 hasPublicationYear "2023" @default.
- W4386880855 type Work @default.
- W4386880855 citedByCount "0" @default.
- W4386880855 crossrefType "journal-article" @default.
- W4386880855 hasAuthorship W4386880855A5065155774 @default.
- W4386880855 hasAuthorship W4386880855A5082323031 @default.
- W4386880855 hasBestOaLocation W43868808551 @default.
- W4386880855 hasConcept C107673813 @default.
- W4386880855 hasConcept C154945302 @default.
- W4386880855 hasConcept C167966045 @default.
- W4386880855 hasConcept C17744445 @default.
- W4386880855 hasConcept C177769412 @default.
- W4386880855 hasConcept C179372163 @default.
- W4386880855 hasConcept C199539241 @default.
- W4386880855 hasConcept C205711294 @default.
- W4386880855 hasConcept C2776359362 @default.
- W4386880855 hasConcept C2781238097 @default.
- W4386880855 hasConcept C31972630 @default.
- W4386880855 hasConcept C39890363 @default.
- W4386880855 hasConcept C41008148 @default.
- W4386880855 hasConcept C94625758 @default.
- W4386880855 hasConceptScore W4386880855C107673813 @default.
- W4386880855 hasConceptScore W4386880855C154945302 @default.
- W4386880855 hasConceptScore W4386880855C167966045 @default.
- W4386880855 hasConceptScore W4386880855C17744445 @default.
- W4386880855 hasConceptScore W4386880855C177769412 @default.
- W4386880855 hasConceptScore W4386880855C179372163 @default.
- W4386880855 hasConceptScore W4386880855C199539241 @default.
- W4386880855 hasConceptScore W4386880855C205711294 @default.
- W4386880855 hasConceptScore W4386880855C2776359362 @default.
- W4386880855 hasConceptScore W4386880855C2781238097 @default.
- W4386880855 hasConceptScore W4386880855C31972630 @default.
- W4386880855 hasConceptScore W4386880855C39890363 @default.
- W4386880855 hasConceptScore W4386880855C41008148 @default.
- W4386880855 hasConceptScore W4386880855C94625758 @default.
- W4386880855 hasFunder F4320327478 @default.
- W4386880855 hasLocation W43868808551 @default.
- W4386880855 hasOpenAccess W4386880855 @default.
- W4386880855 hasPrimaryLocation W43868808551 @default.
- W4386880855 hasRelatedWork W1733683726 @default.
- W4386880855 hasRelatedWork W1837097281 @default.
- W4386880855 hasRelatedWork W1966410754 @default.
- W4386880855 hasRelatedWork W2007544051 @default.
- W4386880855 hasRelatedWork W2325242284 @default.
- W4386880855 hasRelatedWork W2363840281 @default.
- W4386880855 hasRelatedWork W2975200075 @default.
- W4386880855 hasRelatedWork W2981581240 @default.
- W4386880855 hasRelatedWork W3006036127 @default.
- W4386880855 hasRelatedWork W4380558667 @default.
- W4386880855 hasVolume "2023" @default.
- W4386880855 isParatext "false" @default.
- W4386880855 isRetracted "false" @default.
- W4386880855 workType "article" @default.