让3D模型在保留原形的前提下，精准添加精细装饰风格。
OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylization
- 分阶段恢复几何与外观的语义潜在表示，实现内容感知编辑。
- 通过邻近感知填充融合新装饰与原内容，保持整体一致性。
- 零样本推理，支持对形状或外观的可选精细化编辑，适合创意设计者。
文本引导的3D资产风格化对数字内容创作中适应多样视觉美学至关重要。尽管3D形状建模进展迅速，当目标风格涉及细粒度结构装饰时，忠实还原现有资产仍具挑战性，需在保留源几何结构和物体身份的同时，协调融入新风格细节。本文提出 extbf{OrnaStyler}，一种零样本的文本引导装饰感知3D风格化框架。基于修正流生成建模，该方法引入反演引导编辑策略，在几何与外观层面分阶段恢复内容感知的潜在表示，以实现高保真编辑。核心思想是显式建模风格元素的空间布局，缓解体素空间中内容保持与风格表达之间的根本矛盾。具体而言，在几何层面，通过流反演操作操纵体素表示，合成增强装饰的结构，同时保持源资产的空间身份；在外观层面，引入邻近感知特征修复机制，使新生成的装饰与原始内容和谐融合，实现几何-外观的一致集成。本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。在生成数据和真实世界3D资产上的大量实验表明，相比先前方法，OrnaStyler 在内容保持、风格保真度和整体视觉真实性方面均达到最先进水平。代码已开源：https://github.com/tomohiro0427/OrnaStyler
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。