AvatarPerfect: User-Assisted 3D Gaussian Splatting Avatar Refinement with Automatic Pose Suggestion

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sakamiya, Jotaro, Shen, I-Chao, Zhang, Jinsong, Dogan, Mustafa Doga, Igarashi, Takeo
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912163051864064
author Sakamiya, Jotaro
Shen, I-Chao
Zhang, Jinsong
Dogan, Mustafa Doga
Igarashi, Takeo
author_facet Sakamiya, Jotaro
Shen, I-Chao
Zhang, Jinsong
Dogan, Mustafa Doga
Igarashi, Takeo
contents Creating high-quality 3D avatars using 3D Gaussian Splatting (3DGS) from a monocular video benefits virtual reality and telecommunication applications. However, existing automatic methods exhibit artifacts under novel poses due to limited information in the input video. We propose AvatarPerfect, a novel system that allows users to iteratively refine 3DGS avatars by manually editing the rendered avatar images. In each iteration, our system suggests a new body and camera pose to help users identify and correct artifacts. The edited images are then used to update the current avatar, and our system suggests the next body and camera pose for further refinement. To investigate the effectiveness of AvatarPerfect, we conducted a user study comparing our method to an existing 3DGS editor SuperSplat, which allows direct manipulation of Gaussians without automatic pose suggestions. The results indicate that our system enables users to obtain higher quality refined 3DGS avatars than the existing 3DGS editor.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15609
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AvatarPerfect: User-Assisted 3D Gaussian Splatting Avatar Refinement with Automatic Pose Suggestion
Sakamiya, Jotaro
Shen, I-Chao
Zhang, Jinsong
Dogan, Mustafa Doga
Igarashi, Takeo
Human-Computer Interaction
Creating high-quality 3D avatars using 3D Gaussian Splatting (3DGS) from a monocular video benefits virtual reality and telecommunication applications. However, existing automatic methods exhibit artifacts under novel poses due to limited information in the input video. We propose AvatarPerfect, a novel system that allows users to iteratively refine 3DGS avatars by manually editing the rendered avatar images. In each iteration, our system suggests a new body and camera pose to help users identify and correct artifacts. The edited images are then used to update the current avatar, and our system suggests the next body and camera pose for further refinement. To investigate the effectiveness of AvatarPerfect, we conducted a user study comparing our method to an existing 3DGS editor SuperSplat, which allows direct manipulation of Gaussians without automatic pose suggestions. The results indicate that our system enables users to obtain higher quality refined 3DGS avatars than the existing 3DGS editor.
title AvatarPerfect: User-Assisted 3D Gaussian Splatting Avatar Refinement with Automatic Pose Suggestion
topic Human-Computer Interaction
url https://arxiv.org/abs/2412.15609