DreamBarbie: Text to Barbie-Style 3D Avatars
Xiaokun Sun, Zhenyu Zhang, Ying Tai, Hao Tang, Zili Yi, Jian Yang

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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDigital Games and Media
MethodsDiffusion
