AvatarBrush: Monocular Reconstruction of Gaussian Avatars with Intuitive Local Editing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Mengtian, Yao, Shengxiang, Pan, Yichen, Xiao, Haiyao, Li, Zhongmei, Xie, Zhifeng, Chen, Keyu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915635243515904
author Li, Mengtian
Yao, Shengxiang
Pan, Yichen
Xiao, Haiyao
Li, Zhongmei
Xie, Zhifeng
Chen, Keyu
author_facet Li, Mengtian
Yao, Shengxiang
Pan, Yichen
Xiao, Haiyao
Li, Zhongmei
Xie, Zhifeng
Chen, Keyu
contents The efficient reconstruction of high-quality and intuitively editable human avatars presents a pressing challenge in the field of computer vision. Recent advancements, such as 3DGS, have demonstrated impressive reconstruction efficiency and rapid rendering speeds. However, intuitive local editing of these representations remains a significant challenge. In this work, we propose AvatarBrush, a framework that reconstructs fully animatable and locally editable avatars using only a monocular video input. We propose a three-layer model to represent the avatar and, inspired by mesh morphing techniques, design a framework to generate the Gaussian model from local information of the parametric body model. Compared to previous methods that require scanned meshes or multi-view captures as input, our approach reduces costs and enhances editing capabilities such as body shape adjustment, local texture modification, and geometry transfer. Our experimental results demonstrate superior quality across two datasets and emphasize the enhanced, user-friendly, and localized editing capabilities of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19189
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AvatarBrush: Monocular Reconstruction of Gaussian Avatars with Intuitive Local Editing
Li, Mengtian
Yao, Shengxiang
Pan, Yichen
Xiao, Haiyao
Li, Zhongmei
Xie, Zhifeng
Chen, Keyu
Graphics
The efficient reconstruction of high-quality and intuitively editable human avatars presents a pressing challenge in the field of computer vision. Recent advancements, such as 3DGS, have demonstrated impressive reconstruction efficiency and rapid rendering speeds. However, intuitive local editing of these representations remains a significant challenge. In this work, we propose AvatarBrush, a framework that reconstructs fully animatable and locally editable avatars using only a monocular video input. We propose a three-layer model to represent the avatar and, inspired by mesh morphing techniques, design a framework to generate the Gaussian model from local information of the parametric body model. Compared to previous methods that require scanned meshes or multi-view captures as input, our approach reduces costs and enhances editing capabilities such as body shape adjustment, local texture modification, and geometry transfer. Our experimental results demonstrate superior quality across two datasets and emphasize the enhanced, user-friendly, and localized editing capabilities of our method.
title AvatarBrush: Monocular Reconstruction of Gaussian Avatars with Intuitive Local Editing
topic Graphics
url https://arxiv.org/abs/2511.19189