GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor

TL;DR

GaussianAvatar-Editor is a novel framework enabling photorealistic, fully controllable, text-driven editing of 4D Gaussian head avatars, addressing challenges like motion occlusion and temporal consistency with innovative blending and learning techniques.

Contribution

The paper introduces the Weighted Alpha Blending Equation (WABE) and incorporates adversarial learning to improve editing quality and 4D consistency in animatable Gaussian avatars.

Findings

Effective handling of motion occlusion during editing.

Enhanced 4D consistency and realism in avatar animations.

Superior performance over existing methods in experiments.

Abstract

We introduce GaussianAvatar-Editor, an innovative framework for text-driven editing of animatable Gaussian head avatars that can be fully controlled in expression, pose, and viewpoint. Unlike static 3D Gaussian editing, editing animatable 4D Gaussian avatars presents challenges related to motion occlusion and spatial-temporal inconsistency. To address these issues, we propose the Weighted Alpha Blending Equation (WABE). This function enhances the blending weight of visible Gaussians while suppressing the influence on non-visible Gaussians, effectively handling motion occlusion during editing. Furthermore, to improve editing quality and ensure 4D consistency, we incorporate conditional adversarial learning into the editing process. This strategy helps to refine the edited results and maintain consistency throughout the animation. By integrating these methods, our GaussianAvatar-Editor achieves photorealistic and consistent results in animatable 4D Gaussian editing. We conduct comprehensive experiments across various subjects to validate the effectiveness of our proposed techniques, which demonstrates the superiority of our approach over existing methods. More results and code are available at: [Project Link](https://xiangyueliu.github.io/GaussianAvatar-Editor/).