DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion

TL;DR

DreamWaltz-G introduces a novel framework for creating high-quality, animatable 3D avatars from text by integrating skeleton-guided score distillation with a hybrid Gaussian representation, enabling expressive animation and real-time rendering.

Contribution

It proposes Skeleton-guided Score Distillation and a hybrid 3D Gaussian avatar model, improving 3D avatar quality, animation, and rendering efficiency from text prompts.

Findings

Outperforms existing methods in visual quality and expressiveness.

Enables real-time rendering and stable animation.

Supports diverse applications like video reenactment.

Abstract

Leveraging pretrained 2D diffusion models and score distillation sampling (SDS), recent methods have shown promising results for text-to-3D avatar generation. However, generating high-quality 3D avatars capable of expressive animation remains challenging. In this work, we present DreamWaltz-G, a novel learning framework for animatable 3D avatar generation from text. The core of this framework lies in Skeleton-guided Score Distillation and Hybrid 3D Gaussian Avatar representation. Specifically, the proposed skeleton-guided score distillation integrates skeleton controls from 3D human templates into 2D diffusion models, enhancing the consistency of SDS supervision in terms of view and human pose. This facilitates the generation of high-quality avatars, mitigating issues such as multiple faces, extra limbs, and blurring. The proposed hybrid 3D Gaussian avatar representation builds on the efficient 3D Gaussians, combining neural implicit fields and parameterized 3D meshes to enable real-time rendering, stable SDS optimization, and expressive animation. Extensive experiments demonstrate that DreamWaltz-G is highly effective in generating and animating 3D avatars, outperforming existing methods in both visual quality and animation expressiveness. Our framework further supports diverse applications, including human video reenactment and multi-subject scene composition.