Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386076403> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4386076403 abstract "Recently, diffusion models have achieved great success in image synthesis. However, when it comes to the layout-to-image generation where an image often has a complex scene of multiple objects, how to make strong control over both the global layout map and each detailed object remains a challenging task. In this paper, we propose a diffusion model named LayoutDiffusion that can obtain higher generation quality and greater controllability than the previous works. To overcome the difficult multimodal fusion of image and layout, we propose to construct a structural image patch with region information and transform the patched image into a special layout to fuse with the normal layout in a unified form. Moreover, Layout Fusion Module (LFM) and Object-aware Cross Attention (OaCA) are proposed to model the relationship among multiple objects and designed to be object-aware and position-sensitive, allowing for precisely controlling the spatial related information. Extensive experiments show that our LayoutDiffusion out-performs the previous SOTA methods on FID, CAS by relatively 46.35%,26.70% on COCO-stuff and 44.29%,41.82% on VG. Code is available at https://github.com/ZGCTroy/LayoutDiffusion." @default.
- W4386076403 created "2023-08-23" @default.
- W4386076403 creator A5001967719 @default.
- W4386076403 creator A5015095434 @default.
- W4386076403 creator A5039357854 @default.
- W4386076403 creator A5056078581 @default.
- W4386076403 creator A5069354293 @default.
- W4386076403 creator A5088316957 @default.
- W4386076403 date "2023-06-01" @default.
- W4386076403 modified "2023-09-26" @default.
- W4386076403 title "LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation" @default.
- W4386076403 cites W2194775991 @default.
- W4386076403 cites W2277195237 @default.
- W4386076403 cites W2561196672 @default.
- W4386076403 cites W2962770929 @default.
- W4386076403 cites W2962785568 @default.
- W4386076403 cites W2964216930 @default.
- W4386076403 cites W2965833116 @default.
- W4386076403 cites W2987919422 @default.
- W4386076403 cites W2999219213 @default.
- W4386076403 cites W3155072588 @default.
- W4386076403 cites W4312497550 @default.
- W4386076403 cites W4312995674 @default.
- W4386076403 doi "https://doi.org/10.1109/cvpr52729.2023.02154" @default.
- W4386076403 hasPublicationYear "2023" @default.
- W4386076403 type Work @default.
- W4386076403 citedByCount "0" @default.
- W4386076403 crossrefType "proceedings-article" @default.
- W4386076403 hasAuthorship W4386076403A5001967719 @default.
- W4386076403 hasAuthorship W4386076403A5015095434 @default.
- W4386076403 hasAuthorship W4386076403A5039357854 @default.
- W4386076403 hasAuthorship W4386076403A5056078581 @default.
- W4386076403 hasAuthorship W4386076403A5069354293 @default.
- W4386076403 hasAuthorship W4386076403A5088316957 @default.
- W4386076403 hasConcept C115961682 @default.
- W4386076403 hasConcept C119599485 @default.
- W4386076403 hasConcept C127413603 @default.
- W4386076403 hasConcept C141353440 @default.
- W4386076403 hasConcept C154945302 @default.
- W4386076403 hasConcept C177264268 @default.
- W4386076403 hasConcept C199360897 @default.
- W4386076403 hasConcept C201995342 @default.
- W4386076403 hasConcept C2776760102 @default.
- W4386076403 hasConcept C2780451532 @default.
- W4386076403 hasConcept C2780801425 @default.
- W4386076403 hasConcept C2781238097 @default.
- W4386076403 hasConcept C28826006 @default.
- W4386076403 hasConcept C31972630 @default.
- W4386076403 hasConcept C33923547 @default.
- W4386076403 hasConcept C41008148 @default.
- W4386076403 hasConcept C48209547 @default.
- W4386076403 hasConcept C69744172 @default.
- W4386076403 hasConceptScore W4386076403C115961682 @default.
- W4386076403 hasConceptScore W4386076403C119599485 @default.
- W4386076403 hasConceptScore W4386076403C127413603 @default.
- W4386076403 hasConceptScore W4386076403C141353440 @default.
- W4386076403 hasConceptScore W4386076403C154945302 @default.
- W4386076403 hasConceptScore W4386076403C177264268 @default.
- W4386076403 hasConceptScore W4386076403C199360897 @default.
- W4386076403 hasConceptScore W4386076403C201995342 @default.
- W4386076403 hasConceptScore W4386076403C2776760102 @default.
- W4386076403 hasConceptScore W4386076403C2780451532 @default.
- W4386076403 hasConceptScore W4386076403C2780801425 @default.
- W4386076403 hasConceptScore W4386076403C2781238097 @default.
- W4386076403 hasConceptScore W4386076403C28826006 @default.
- W4386076403 hasConceptScore W4386076403C31972630 @default.
- W4386076403 hasConceptScore W4386076403C33923547 @default.
- W4386076403 hasConceptScore W4386076403C41008148 @default.
- W4386076403 hasConceptScore W4386076403C48209547 @default.
- W4386076403 hasConceptScore W4386076403C69744172 @default.
- W4386076403 hasFunder F4320321001 @default.
- W4386076403 hasFunder F4320335777 @default.
- W4386076403 hasLocation W43860764031 @default.
- W4386076403 hasOpenAccess W4386076403 @default.
- W4386076403 hasPrimaryLocation W43860764031 @default.
- W4386076403 hasRelatedWork W1837097281 @default.
- W4386076403 hasRelatedWork W2007544051 @default.
- W4386076403 hasRelatedWork W2010729749 @default.
- W4386076403 hasRelatedWork W2023827232 @default.
- W4386076403 hasRelatedWork W2184797770 @default.
- W4386076403 hasRelatedWork W2419576664 @default.
- W4386076403 hasRelatedWork W2912737833 @default.
- W4386076403 hasRelatedWork W2975200075 @default.
- W4386076403 hasRelatedWork W2991316108 @default.
- W4386076403 hasRelatedWork W4312613727 @default.
- W4386076403 isParatext "false" @default.
- W4386076403 isRetracted "false" @default.
- W4386076403 workType "article" @default.