HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMs

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sevastopolsky, Artem, Grassal, Philip-William, Giebenhain, Simon, Athar, ShahRukh, Verdoliva, Luisa, Niessner, Matthias
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909470362173440
author Sevastopolsky, Artem
Grassal, Philip-William
Giebenhain, Simon
Athar, ShahRukh
Verdoliva, Luisa
Niessner, Matthias
author_facet Sevastopolsky, Artem
Grassal, Philip-William
Giebenhain, Simon
Athar, ShahRukh
Verdoliva, Luisa
Niessner, Matthias
contents Current advances in human head modeling allow the generation of plausible-looking 3D head models via neural representations, such as NeRFs and SDFs. Nevertheless, constructing complete high-fidelity head models with explicitly controlled animation remains an issue. Furthermore, completing the head geometry based on a partial observation, e.g., coming from a depth sensor, while preserving a high level of detail is often problematic for the existing methods. We introduce a generative model for detailed 3D head meshes on top of an articulated 3DMM, simultaneously allowing explicit animation and high-detail preservation. Our method is trained in two stages. First, we register a parametric head model with vertex displacements to each mesh of the recently introduced NPHM dataset of accurate 3D head scans. The estimated displacements are baked into a hand-crafted UV layout. Second, we train a StyleGAN model to generalize over the UV maps of displacements, which we later refer to as HeadCraft. The decomposition of the parametric model and high-quality vertex displacements allows us to animate the model and modify the regions semantically. We demonstrate the results of unconditional sampling, fitting to a scan and editing. The project page is available at https://seva100.github.io/headcraft.
format Preprint
id arxiv_https___arxiv_org_abs_2312_14140
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMs
Sevastopolsky, Artem
Grassal, Philip-William
Giebenhain, Simon
Athar, ShahRukh
Verdoliva, Luisa
Niessner, Matthias
Computer Vision and Pattern Recognition
Current advances in human head modeling allow the generation of plausible-looking 3D head models via neural representations, such as NeRFs and SDFs. Nevertheless, constructing complete high-fidelity head models with explicitly controlled animation remains an issue. Furthermore, completing the head geometry based on a partial observation, e.g., coming from a depth sensor, while preserving a high level of detail is often problematic for the existing methods. We introduce a generative model for detailed 3D head meshes on top of an articulated 3DMM, simultaneously allowing explicit animation and high-detail preservation. Our method is trained in two stages. First, we register a parametric head model with vertex displacements to each mesh of the recently introduced NPHM dataset of accurate 3D head scans. The estimated displacements are baked into a hand-crafted UV layout. Second, we train a StyleGAN model to generalize over the UV maps of displacements, which we later refer to as HeadCraft. The decomposition of the parametric model and high-quality vertex displacements allows us to animate the model and modify the regions semantically. We demonstrate the results of unconditional sampling, fitting to a scan and editing. The project page is available at https://seva100.github.io/headcraft.
title HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.14140