DreamStyle3D：通过双注意力解缠实现高效3D风格化资产生成
DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement
浏览论文内容
中文总结 AI 辅助
针对高效生成风格化3D资产的需求，DreamStyle3D基于解耦双交叉注意力机制，明确分离几何与风格特征，采用轻量级训练策略，构建数据集和数据管道，能在10秒内生成高质量、几何一致的风格化3D资产，提升了效率并为3D创作提供新方案。
中文摘要 AI 辅助
随着游戏、动画和虚拟现实行业的发展，对高效生成风格化3D资产的需求迅速增长。现有方法在保持风格保真度、几何一致性和生成效率方面仍存在困难。为此，我们提出了DreamStyle3D，一个基于解耦双交叉注意力机制的高效风格化3D资产生成框架。该方法明确分离几何和风格特征，采用轻量级训练策略。我们构建了自动数据管道和数据集。实验表明，DreamStyle3D能在10秒内生成高质量、几何一致的风格化3D资产，提高了效率并提供了新的3D内容创作解决方案。
英文摘要
With the growth of gaming, animation, and virtual reality industries, the demand for efficient generation of stylized 3D assets is rapidly increasing. However, existing approaches still struggle to jointly preserve style fidelity, geometric consistency, and generation efficiency, as most of them still rely on indirect 2D-to-3D stylization pipelines. This motivates a native 3D stylization framework that can explicitly disentangle style from geometry while remaining efficient. To this end, we propose DreamStyle3D, an efficient framework for stylized 3D asset generation built on a Decoupled Dual Cross-Attention mechanism. Our method explicitly separates geometric and stylistic features to enable efficient style injection while preserving structural consistency, and further adopts a lightweight training strategy to enhance style consistency and model generalization. In addition, we build an automated data pipeline and construct a dataset of about 15K content-style-stylized triplets for training and evaluation. Extensive experiments demonstrate that our DreamStyle3D can generate high-fidelity, geometrically consistent stylized 3D assets within 10 seconds, substantially improving efficiency while maintaining superior style quality and offering a new solution for 3D content creation. The project is available at https://github.com/NK-JittorCV/nk-3D/tree/main/models/DreamStyle3D.
发表机构
- VCIP, Nankai University（视觉计算与图像处理实验室，南开大学）
- JD Explore Academy（京东探索研究院）
- AAIS, Nankai University（人工智能学院，南开大学）
机构由 AI 辅助整理，请以论文原文为准。
