Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297889075> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4297889075 abstract "In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs. While plenty of works extend unconditional generative models and achieve some levels of controllability, it is still challenging to ensure multi-view consistency, especially in large poses. In this work, we propose a network that generates 3D-aware portraits while being controllable according to semantic parameters regarding pose, identity, expression and illumination. Our network uses neural scene representation to model 3D-aware portraits, whose generation is guided by a parametric face model that supports explicit control. While the latent disentanglement can be further enhanced by contrasting images with partially different attributes, there still exists noticeable inconsistency in non-face areas, e.g., hair and background, when animating expressions. Wesolve this by proposing a volume blending strategy in which we form a composite output by blending dynamic and static areas, with two parts segmented from the jointly learned semantic field. Our method outperforms prior arts in extensive experiments, producing realistic portraits with vivid expression in natural lighting when viewed from free viewpoints. It also demonstrates generalization ability to real images as well as out-of-domain data, showing great promise in real applications." @default.
- W4297889075 created "2022-10-01" @default.
- W4297889075 creator A5001330715 @default.
- W4297889075 creator A5011877804 @default.
- W4297889075 creator A5013134358 @default.
- W4297889075 creator A5030587413 @default.
- W4297889075 creator A5045789612 @default.
- W4297889075 creator A5084218062 @default.
- W4297889075 creator A5088174174 @default.
- W4297889075 date "2022-09-12" @default.
- W4297889075 modified "2023-09-23" @default.
- W4297889075 title "3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation" @default.
- W4297889075 doi "https://doi.org/10.48550/arxiv.2209.05434" @default.
- W4297889075 hasPublicationYear "2022" @default.
- W4297889075 type Work @default.
- W4297889075 citedByCount "0" @default.
- W4297889075 crossrefType "posted-content" @default.
- W4297889075 hasAuthorship W4297889075A5001330715 @default.
- W4297889075 hasAuthorship W4297889075A5011877804 @default.
- W4297889075 hasAuthorship W4297889075A5013134358 @default.
- W4297889075 hasAuthorship W4297889075A5030587413 @default.
- W4297889075 hasAuthorship W4297889075A5045789612 @default.
- W4297889075 hasAuthorship W4297889075A5084218062 @default.
- W4297889075 hasAuthorship W4297889075A5088174174 @default.
- W4297889075 hasBestOaLocation W42978890751 @default.
- W4297889075 hasConcept C111919701 @default.
- W4297889075 hasConcept C134306372 @default.
- W4297889075 hasConcept C142362112 @default.
- W4297889075 hasConcept C144024400 @default.
- W4297889075 hasConcept C153349607 @default.
- W4297889075 hasConcept C154945302 @default.
- W4297889075 hasConcept C167966045 @default.
- W4297889075 hasConcept C177148314 @default.
- W4297889075 hasConcept C17744445 @default.
- W4297889075 hasConcept C199360897 @default.
- W4297889075 hasConcept C199539241 @default.
- W4297889075 hasConcept C2776035091 @default.
- W4297889075 hasConcept C2776359362 @default.
- W4297889075 hasConcept C2776436953 @default.
- W4297889075 hasConcept C2779304628 @default.
- W4297889075 hasConcept C31972630 @default.
- W4297889075 hasConcept C33923547 @default.
- W4297889075 hasConcept C36289849 @default.
- W4297889075 hasConcept C39890363 @default.
- W4297889075 hasConcept C41008148 @default.
- W4297889075 hasConcept C43521106 @default.
- W4297889075 hasConcept C94625758 @default.
- W4297889075 hasConcept C98045186 @default.
- W4297889075 hasConceptScore W4297889075C111919701 @default.
- W4297889075 hasConceptScore W4297889075C134306372 @default.
- W4297889075 hasConceptScore W4297889075C142362112 @default.
- W4297889075 hasConceptScore W4297889075C144024400 @default.
- W4297889075 hasConceptScore W4297889075C153349607 @default.
- W4297889075 hasConceptScore W4297889075C154945302 @default.
- W4297889075 hasConceptScore W4297889075C167966045 @default.
- W4297889075 hasConceptScore W4297889075C177148314 @default.
- W4297889075 hasConceptScore W4297889075C17744445 @default.
- W4297889075 hasConceptScore W4297889075C199360897 @default.
- W4297889075 hasConceptScore W4297889075C199539241 @default.
- W4297889075 hasConceptScore W4297889075C2776035091 @default.
- W4297889075 hasConceptScore W4297889075C2776359362 @default.
- W4297889075 hasConceptScore W4297889075C2776436953 @default.
- W4297889075 hasConceptScore W4297889075C2779304628 @default.
- W4297889075 hasConceptScore W4297889075C31972630 @default.
- W4297889075 hasConceptScore W4297889075C33923547 @default.
- W4297889075 hasConceptScore W4297889075C36289849 @default.
- W4297889075 hasConceptScore W4297889075C39890363 @default.
- W4297889075 hasConceptScore W4297889075C41008148 @default.
- W4297889075 hasConceptScore W4297889075C43521106 @default.
- W4297889075 hasConceptScore W4297889075C94625758 @default.
- W4297889075 hasConceptScore W4297889075C98045186 @default.
- W4297889075 hasLocation W42978890751 @default.
- W4297889075 hasOpenAccess W4297889075 @default.
- W4297889075 hasPrimaryLocation W42978890751 @default.
- W4297889075 hasRelatedWork W1899364738 @default.
- W4297889075 hasRelatedWork W1955116508 @default.
- W4297889075 hasRelatedWork W1966276047 @default.
- W4297889075 hasRelatedWork W2023301637 @default.
- W4297889075 hasRelatedWork W2103413230 @default.
- W4297889075 hasRelatedWork W2136321227 @default.
- W4297889075 hasRelatedWork W2328068029 @default.
- W4297889075 hasRelatedWork W2334336442 @default.
- W4297889075 hasRelatedWork W2908959303 @default.
- W4297889075 hasRelatedWork W43171467 @default.
- W4297889075 isParatext "false" @default.
- W4297889075 isRetracted "false" @default.
- W4297889075 workType "article" @default.