DreamBarbie: Text to Barbie-Style 3D Avatars

TL;DR

DreamBarbie introduces a novel text-driven framework for creating high-quality, animatable 3D Barbie-style avatars with disentangled components, leveraging an expressive 3D representation and specialized diffusion models for diverse applications.

Contribution

It presents a new G-Shell based 3D modeling approach with SDF initialization and a hole regularization loss, enabling fast, stable, and detailed avatar generation from text without image input.

Findings

Outperforms existing methods in dressed human and outfit generation.

Achieves 100x speedup with stable open topology.

Enables diverse applications like apparel editing and animation.

Abstract

To integrate digital humans into everyday life, there is a strong demand for generating high-quality, fine-grained disentangled 3D avatars that support expressive animation and simulation capabilities, ideally from low-cost textual inputs. Although text-driven 3D avatar generation has made significant progress by leveraging 2D generative priors, existing methods still struggle to fulfill all these requirements simultaneously. To address this challenge, we propose DreamBarbie, a novel text-driven framework for generating animatable 3D avatars with separable shoes, accessories, and simulation-ready garments, truly capturing the iconic ``Barbie doll'' aesthetic. The core of our framework lies in an expressive 3D representation combined with appropriate modeling constraints. Unlike prior methods, we use G-Shell to uniformly model watertight components (e.g., bodies, shoes) and non-watertight garments. By reformulating boundaries as Euclidean field intersections instead of manifold geodesics, we propose an SDF-based initialization and a hole regularization loss that together achieve a 100x speedup and stable open topology without image input. These disentangled 3D representations are then optimized by specialized expert diffusion models tailored to each domain, ensuring high-fidelity outputs. To mitigate geometric artifacts and texture conflicts when combining different expert models, we further propose several effective geometric losses and strategies. Extensive experiments demonstrate that DreamBarbie outperforms existing methods in both dressed human and outfit generation. Our framework further enables diverse applications, including apparel combination, editing, expressive animation, and physical simulation. Project page: https://xiaokunsun.github.io/DreamBarbie.github.io/.