Détail du document
Identifiant
oai:arXiv.org:2411.01512
Sujet
Computer Science - Computer Vision... Computer Science - GraphicsAuteur
Budria, Alvaro Lopez-Rodriguez, Adrian Lorente, Oscar Moreno-Noguer, FrancescCatégorie
Computer Science
Année
2024
Date de référencement
04/12/2024
Mots clés
avatars instantgeoavatar computerRésumé
We present InstantGeoAvatar, a method for efficient and effective learning from monocular video of detailed 3D geometry and appearance of animatable implicit human avatars.
Our key observation is that the optimization of a hash grid encoding to represent a signed distance function (SDF) of the human subject is fraught with instabilities and bad local minima.
We thus propose a principled geometry-aware SDF regularization scheme that seamlessly fits into the volume rendering pipeline and adds negligible computational overhead.
Our regularization scheme significantly outperforms previous approaches for training SDFs on hash grids.
We obtain competitive results in geometry reconstruction and novel view synthesis in as little as five minutes of training time, a significant reduction from the several hours required by previous work.
InstantGeoAvatar represents a significant leap forward towards achieving interactive reconstruction of virtual avatars.
;Comment: Accepted as poster to Asian Conference on Computer Vison (ACCV 2024)
Budria, Alvaro,Lopez-Rodriguez, Adrian,Lorente, Oscar,Moreno-Noguer, Francesc, 2024, InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video
Clinical Relevance of Plaque Distribution for Basilar Artery Stenosis
study endovascular imaging wall basilar complications plaque postoperative artery plaques stenosis
