Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377010131> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4377010131 abstract "In this paper, we introduce FitMe, a facial reflectance model and a differentiable rendering optimization pipeline, that can be used to acquire high-fidelity renderable human avatars from single or multiple images. The model consists of a multi-modal style-based generator, that captures facial appearance in terms of diffuse and specular reflectance, and a PCA-based shape model. We employ a fast differentiable rendering process that can be used in an optimization pipeline, while also achieving photorealistic facial shading. Our optimization process accurately captures both the facial reflectance and shape in high-detail, by exploiting the expressivity of the style-based latent representation and of our shape model. FitMe achieves state-of-the-art reflectance acquisition and identity preservation on single in-the-wild facial images, while it produces impressive scan-like results, when given multiple unconstrained facial images pertaining to the same identity. In contrast with recent implicit avatar reconstructions, FitMe requires only one minute and produces relightable mesh and texture-based avatars, that can be used by end-user applications." @default.
- W4377010131 created "2023-05-19" @default.
- W4377010131 creator A5043197698 @default.
- W4377010131 creator A5073110676 @default.
- W4377010131 creator A5074709231 @default.
- W4377010131 creator A5080553022 @default.
- W4377010131 creator A5081021169 @default.
- W4377010131 creator A5088913907 @default.
- W4377010131 date "2023-05-16" @default.
- W4377010131 modified "2023-09-29" @default.
- W4377010131 title "FitMe: Deep Photorealistic 3D Morphable Model Avatars" @default.
- W4377010131 doi "https://doi.org/10.48550/arxiv.2305.09641" @default.
- W4377010131 hasPublicationYear "2023" @default.
- W4377010131 type Work @default.
- W4377010131 citedByCount "0" @default.
- W4377010131 crossrefType "posted-content" @default.
- W4377010131 hasAuthorship W4377010131A5043197698 @default.
- W4377010131 hasAuthorship W4377010131A5073110676 @default.
- W4377010131 hasAuthorship W4377010131A5074709231 @default.
- W4377010131 hasAuthorship W4377010131A5080553022 @default.
- W4377010131 hasAuthorship W4377010131A5081021169 @default.
- W4377010131 hasAuthorship W4377010131A5088913907 @default.
- W4377010131 hasBestOaLocation W43770101311 @default.
- W4377010131 hasConcept C115961682 @default.
- W4377010131 hasConcept C121684516 @default.
- W4377010131 hasConcept C154945302 @default.
- W4377010131 hasConcept C205711294 @default.
- W4377010131 hasConcept C31972630 @default.
- W4377010131 hasConcept C41008148 @default.
- W4377010131 hasConcept C83248878 @default.
- W4377010131 hasConceptScore W4377010131C115961682 @default.
- W4377010131 hasConceptScore W4377010131C121684516 @default.
- W4377010131 hasConceptScore W4377010131C154945302 @default.
- W4377010131 hasConceptScore W4377010131C205711294 @default.
- W4377010131 hasConceptScore W4377010131C31972630 @default.
- W4377010131 hasConceptScore W4377010131C41008148 @default.
- W4377010131 hasConceptScore W4377010131C83248878 @default.
- W4377010131 hasLocation W43770101311 @default.
- W4377010131 hasOpenAccess W4377010131 @default.
- W4377010131 hasPrimaryLocation W43770101311 @default.
- W4377010131 hasRelatedWork W1503414886 @default.
- W4377010131 hasRelatedWork W1863533157 @default.
- W4377010131 hasRelatedWork W1972983025 @default.
- W4377010131 hasRelatedWork W2048402902 @default.
- W4377010131 hasRelatedWork W2087353037 @default.
- W4377010131 hasRelatedWork W2095660797 @default.
- W4377010131 hasRelatedWork W2143214896 @default.
- W4377010131 hasRelatedWork W2166044122 @default.
- W4377010131 hasRelatedWork W2740010476 @default.
- W4377010131 hasRelatedWork W3182299699 @default.
- W4377010131 isParatext "false" @default.
- W4377010131 isRetracted "false" @default.
- W4377010131 workType "article" @default.