Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386081121> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4386081121 abstract "Despite significant progress in Text-to-Image (T2I) generative models, even lengthy and complex text descriptions still struggle to convey detailed controls. In contrast, Layout-to-Image (L2I) generation, aiming to generate realistic and complex scene images from user-specified layouts, has risen to prominence. However, existing methods transform layout information into tokens or RGB images for conditional control in the generative process, leading to insufficient spatial and semantic controllability of individual instances. To address these limitations, we propose a novel Spatial-Semantic Map Guided (SSMG) diffusion model that adopts the feature map, derived from the layout, as guidance. Owing to rich spatial and semantic information encapsulated in well-designed feature maps, SSMG achieves superior generation quality with sufficient spatial and semantic controllability compared to previous works. Additionally, we propose the Relation-Sensitive Attention (RSA) and Location-Sensitive Attention (LSA) mechanisms. The former aims to model the relationships among multiple objects within scenes while the latter is designed to heighten the model's sensitivity to the spatial information embedded in the guidance. Extensive experiments demonstrate that SSMG achieves highly promising results, setting a new state-of-the-art across a range of metrics encompassing fidelity, diversity, and controllability." @default.
- W4386081121 created "2023-08-23" @default.
- W4386081121 creator A5009687619 @default.
- W4386081121 creator A5013911439 @default.
- W4386081121 creator A5034967388 @default.
- W4386081121 creator A5062654071 @default.
- W4386081121 creator A5069522797 @default.
- W4386081121 creator A5075880303 @default.
- W4386081121 creator A5082439195 @default.
- W4386081121 date "2023-08-20" @default.
- W4386081121 modified "2023-09-27" @default.
- W4386081121 title "SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-form Layout-to-Image Generation" @default.
- W4386081121 doi "https://doi.org/10.48550/arxiv.2308.10156" @default.
- W4386081121 hasPublicationYear "2023" @default.
- W4386081121 type Work @default.
- W4386081121 citedByCount "0" @default.
- W4386081121 crossrefType "posted-content" @default.
- W4386081121 hasAuthorship W4386081121A5009687619 @default.
- W4386081121 hasAuthorship W4386081121A5013911439 @default.
- W4386081121 hasAuthorship W4386081121A5034967388 @default.
- W4386081121 hasAuthorship W4386081121A5062654071 @default.
- W4386081121 hasAuthorship W4386081121A5069522797 @default.
- W4386081121 hasAuthorship W4386081121A5075880303 @default.
- W4386081121 hasAuthorship W4386081121A5082439195 @default.
- W4386081121 hasBestOaLocation W43860811211 @default.
- W4386081121 hasConcept C105795698 @default.
- W4386081121 hasConcept C111919701 @default.
- W4386081121 hasConcept C115961682 @default.
- W4386081121 hasConcept C124101348 @default.
- W4386081121 hasConcept C138885662 @default.
- W4386081121 hasConcept C154945302 @default.
- W4386081121 hasConcept C159620131 @default.
- W4386081121 hasConcept C167966045 @default.
- W4386081121 hasConcept C184337299 @default.
- W4386081121 hasConcept C199360897 @default.
- W4386081121 hasConcept C25343380 @default.
- W4386081121 hasConcept C2776401178 @default.
- W4386081121 hasConcept C2776459999 @default.
- W4386081121 hasConcept C28826006 @default.
- W4386081121 hasConcept C33923547 @default.
- W4386081121 hasConcept C39890363 @default.
- W4386081121 hasConcept C41008148 @default.
- W4386081121 hasConcept C41895202 @default.
- W4386081121 hasConcept C48209547 @default.
- W4386081121 hasConcept C76155785 @default.
- W4386081121 hasConcept C98045186 @default.
- W4386081121 hasConceptScore W4386081121C105795698 @default.
- W4386081121 hasConceptScore W4386081121C111919701 @default.
- W4386081121 hasConceptScore W4386081121C115961682 @default.
- W4386081121 hasConceptScore W4386081121C124101348 @default.
- W4386081121 hasConceptScore W4386081121C138885662 @default.
- W4386081121 hasConceptScore W4386081121C154945302 @default.
- W4386081121 hasConceptScore W4386081121C159620131 @default.
- W4386081121 hasConceptScore W4386081121C167966045 @default.
- W4386081121 hasConceptScore W4386081121C184337299 @default.
- W4386081121 hasConceptScore W4386081121C199360897 @default.
- W4386081121 hasConceptScore W4386081121C25343380 @default.
- W4386081121 hasConceptScore W4386081121C2776401178 @default.
- W4386081121 hasConceptScore W4386081121C2776459999 @default.
- W4386081121 hasConceptScore W4386081121C28826006 @default.
- W4386081121 hasConceptScore W4386081121C33923547 @default.
- W4386081121 hasConceptScore W4386081121C39890363 @default.
- W4386081121 hasConceptScore W4386081121C41008148 @default.
- W4386081121 hasConceptScore W4386081121C41895202 @default.
- W4386081121 hasConceptScore W4386081121C48209547 @default.
- W4386081121 hasConceptScore W4386081121C76155785 @default.
- W4386081121 hasConceptScore W4386081121C98045186 @default.
- W4386081121 hasLocation W43860811211 @default.
- W4386081121 hasOpenAccess W4386081121 @default.
- W4386081121 hasPrimaryLocation W43860811211 @default.
- W4386081121 hasRelatedWork W2888227225 @default.
- W4386081121 hasRelatedWork W2953950067 @default.
- W4386081121 hasRelatedWork W2971193605 @default.
- W4386081121 hasRelatedWork W3034360859 @default.
- W4386081121 hasRelatedWork W4205201592 @default.
- W4386081121 hasRelatedWork W4221155573 @default.
- W4386081121 hasRelatedWork W4283217443 @default.
- W4386081121 hasRelatedWork W4285886406 @default.
- W4386081121 hasRelatedWork W4300104287 @default.
- W4386081121 hasRelatedWork W4380136907 @default.
- W4386081121 isParatext "false" @default.
- W4386081121 isRetracted "false" @default.
- W4386081121 workType "article" @default.