AvatarBrush: Monocular Reconstruction of Gaussian Avatars with Intuitive Local Editing

TL;DR

AvatarBrush enables high-quality, fully animatable, and locally editable human avatars from monocular videos, significantly reducing input costs and enhancing editing capabilities compared to previous methods.

Contribution

We introduce AvatarBrush, a novel framework that reconstructs editable Gaussian avatars from monocular videos, improving editing flexibility and reducing input requirements.

Findings

Superior reconstruction quality on two datasets

Enhanced local editing capabilities

Reduced input costs compared to multi-view methods

Abstract

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.