发表机构
University of Fukui; Toyohashi University of Technology; CyberAgent, Inc.（福井大学; 丰桥技术科学大学; CyberAgent公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
OrnaStyler是一种零样本3D风格化框架，通过分阶段恢复几何与外观层面的潜在表示，实现文本引导下兼顾内容保留与风格表达的3D资产装饰编辑，性能优于现有方法
AI 中文摘要
文本引导的3D资产风格编辑对于数字内容创作中使现有对象适配多样化视觉美学至关重要。尽管3D形状建模取得了快速进展，但当所需风格化涉及细粒度结构装饰时，忠实风格化现有资产仍具挑战性，这要求模型在保留源几何和对象身份的同时，连贯整合新的风格特定细节。我们提出OrnaStyler，一种用于文本引导的感知装饰3D风格化的零样本框架。该框架基于整流流生成建模构建，引入了倒置引导编辑策略，分阶段恢复几何和外观层面的内容感知潜在表示以实现忠实编辑。我们的核心思想是显式建模风格元素的空间配置，从而缓解体素空间中内容保留与风格表达之间的根本矛盾。具体而言，在几何层面，我们通过流倒置操作体素表示，合成装饰增强的结构，同时保留源资产的空间身份；在外观层面，我们引入邻接感知特征修复机制，使新生成的装饰与原始内容协调，实现几何与外观的连贯整合。我们的方法仅在推理阶段运行，支持对几何增强或外观风格化的选择性编辑。在生成的和真实世界的3D资产上与现有方法进行的大量实验表明，OrnaStyler在内容保留、风格保真度和整体视觉真实感方面达到了最先进的编辑性能。代码可在：this https URL获取
英文摘要
Text-guided style editing of 3D assets is essential for adapting existing objects to diverse visual aesthetics in digital content creation. Despite rapid progress in 3D shape modeling, faithfully stylizing an existing asset remains challenging when the desired stylization involves fine-grained structural ornamentation, which requires the model to preserve the source geometry and object identity, while coherently integrating new style-specific details. We propose \textbf{OrnaStyler}, a zero-shot framework for text-guided ornament-aware 3D stylization. Built upon rectified flow-based generative modeling, OrnaStyler introduces an inversion-guided editing strategy that recovers content-aware latent representations at both geometry and appearance levels in a staged manner to facilitate faithful editing. Our core idea is to explicitly model the spatial configuration of stylistic elements, thereby mitigating the fundamental tension between content preservation and style expression in the voxel space. Specifically, at the geometry level, we manipulate voxel representations through flow inversion to synthesize ornament-enhanced structures while preserving the spatial identity of the source asset. Then, at the appearance level, we introduce an adjacency-aware feature inpainting mechanism to harmonize newly generated ornaments with the original content, yielding coherent geometry-appearance integration. Our approach operates solely in the inference phase and enables selective editing over geometric augmentation or appearance stylization. Extensive experiments on both generated and real-world 3D assets against prior methods demonstrate that OrnaStyler achieves state-of-the-art editing performance in terms of content preservation, style fidelity, and overall visual realism. Code is available at: https://github.com/tomohiro0427/OrnaStyler
