Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307206535> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4307206535 abstract "Photo-real digital human avatars are of enormous importance in graphics, as they enable immersive communication over the globe, improve gaming and entertainment experiences, and can be particularly beneficial for AR and VR settings. However, current avatar generation approaches either fall short in high-fidelity novel view synthesis, generalization to novel motions, reproduction of loose clothing, or they cannot render characters at the high resolution offered by modern displays. To this end, we propose HDHumans, which is the first method for HD human character synthesis that jointly produces an accurate and temporally coherent 3D deforming surface and highly photo-realistic images of arbitrary novel views and of motions not seen at training time. At the technical core, our method tightly integrates a classical deforming character template with neural radiance fields (NeRF). Our method is carefully designed to achieve a synergy between classical surface deformation and NeRF. First, the template guides the NeRF, which allows synthesizing novel views of a highly dynamic and articulated character and even enables the synthesis of novel motions. Second, we also leverage the dense pointclouds resulting from NeRF to further improve the deforming surface via 3D-to-3D supervision. We outperform the state of the art quantitatively and qualitatively in terms of synthesis quality and resolution, as well as the quality of 3D surface reconstruction." @default.
- W4307206535 created "2022-10-30" @default.
- W4307206535 creator A5020664641 @default.
- W4307206535 creator A5039500794 @default.
- W4307206535 creator A5044917356 @default.
- W4307206535 creator A5056083424 @default.
- W4307206535 creator A5076908763 @default.
- W4307206535 creator A5087345525 @default.
- W4307206535 date "2022-10-21" @default.
- W4307206535 modified "2023-09-27" @default.
- W4307206535 title "HDHumans: A Hybrid Approach for High-fidelity Digital Humans" @default.
- W4307206535 doi "https://doi.org/10.48550/arxiv.2210.12003" @default.
- W4307206535 hasPublicationYear "2022" @default.
- W4307206535 type Work @default.
- W4307206535 citedByCount "0" @default.
- W4307206535 crossrefType "posted-content" @default.
- W4307206535 hasAuthorship W4307206535A5020664641 @default.
- W4307206535 hasAuthorship W4307206535A5039500794 @default.
- W4307206535 hasAuthorship W4307206535A5044917356 @default.
- W4307206535 hasAuthorship W4307206535A5056083424 @default.
- W4307206535 hasAuthorship W4307206535A5076908763 @default.
- W4307206535 hasAuthorship W4307206535A5087345525 @default.
- W4307206535 hasBestOaLocation W43072065351 @default.
- W4307206535 hasConcept C107457646 @default.
- W4307206535 hasConcept C113364801 @default.
- W4307206535 hasConcept C121332964 @default.
- W4307206535 hasConcept C121684516 @default.
- W4307206535 hasConcept C153083717 @default.
- W4307206535 hasConcept C154945302 @default.
- W4307206535 hasConcept C24890656 @default.
- W4307206535 hasConcept C2524010 @default.
- W4307206535 hasConcept C2776459999 @default.
- W4307206535 hasConcept C2777365542 @default.
- W4307206535 hasConcept C2780861071 @default.
- W4307206535 hasConcept C31972630 @default.
- W4307206535 hasConcept C33923547 @default.
- W4307206535 hasConcept C41008148 @default.
- W4307206535 hasConcept C502989409 @default.
- W4307206535 hasConcept C69369342 @default.
- W4307206535 hasConcept C76155785 @default.
- W4307206535 hasConcept C90697248 @default.
- W4307206535 hasConceptScore W4307206535C107457646 @default.
- W4307206535 hasConceptScore W4307206535C113364801 @default.
- W4307206535 hasConceptScore W4307206535C121332964 @default.
- W4307206535 hasConceptScore W4307206535C121684516 @default.
- W4307206535 hasConceptScore W4307206535C153083717 @default.
- W4307206535 hasConceptScore W4307206535C154945302 @default.
- W4307206535 hasConceptScore W4307206535C24890656 @default.
- W4307206535 hasConceptScore W4307206535C2524010 @default.
- W4307206535 hasConceptScore W4307206535C2776459999 @default.
- W4307206535 hasConceptScore W4307206535C2777365542 @default.
- W4307206535 hasConceptScore W4307206535C2780861071 @default.
- W4307206535 hasConceptScore W4307206535C31972630 @default.
- W4307206535 hasConceptScore W4307206535C33923547 @default.
- W4307206535 hasConceptScore W4307206535C41008148 @default.
- W4307206535 hasConceptScore W4307206535C502989409 @default.
- W4307206535 hasConceptScore W4307206535C69369342 @default.
- W4307206535 hasConceptScore W4307206535C76155785 @default.
- W4307206535 hasConceptScore W4307206535C90697248 @default.
- W4307206535 hasLocation W43072065351 @default.
- W4307206535 hasLocation W43072065352 @default.
- W4307206535 hasOpenAccess W4307206535 @default.
- W4307206535 hasPrimaryLocation W43072065351 @default.
- W4307206535 hasRelatedWork W162395460 @default.
- W4307206535 hasRelatedWork W2028717905 @default.
- W4307206535 hasRelatedWork W2139395280 @default.
- W4307206535 hasRelatedWork W3138581055 @default.
- W4307206535 hasRelatedWork W3152606049 @default.
- W4307206535 hasRelatedWork W4255542975 @default.
- W4307206535 hasRelatedWork W4281779882 @default.
- W4307206535 hasRelatedWork W4297959415 @default.
- W4307206535 hasRelatedWork W919641001 @default.
- W4307206535 hasRelatedWork W2555438592 @default.
- W4307206535 isParatext "false" @default.
- W4307206535 isRetracted "false" @default.
- W4307206535 workType "article" @default.