Owner3D：基于所有权引导风格写入的无训练本地化3D风格化方法
Owner3D: Ownership-Guided Style Writing for Training-Free Localized 3D Stylization
- College of Computer Science, Sichuan University（四川大学计算机学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究针对LRM中本地化3D风格化的风格泄漏与边界模糊问题，提出无训练框架Owner3D，通过所有权引导风格写入、边界双槽及表面优先纹理读出实现更优的风格保真与外观保留。
AI中文摘要：
本地化3D风格化旨在修改指定对象部分的外观，同时保留其余表面。在大型重建模型（LRMs）中，该任务颇具挑战性，因为风格会在渲染前注入中间外观表示，而紧凑的三平面特征会在目标与非目标表面间共享，导致风格泄漏和边界模糊。我们提出Owner3D，一种无训练的本地化3D风格化框架，它将本地化外观控制直接整合到LRM重建过程中。具体而言，Owner3D引入所有权引导风格写入，将参考风格的注入限制在目标区域，生成单一的本地化风格化三平面，无需额外训练，同时避免使用独立的全局风格与外观表示。为解决语义边界附近的外观模糊问题，我们进一步引入边界双槽，为目标与非目标区域维护独立的局部特征源。最后，表面优先纹理读出以分层方式结合表面、3D和三平面所有权证据，在可见性不完整时稳健恢复外观。在由Google Scanned Objects和PartNet构建的基准上进行的实验表明，Owner3D在目标区域风格保真度和非目标外观保留方面始终优于现有3D风格化方法，与StyleSplat和LAENeRF相比，分别减少了86.4%和89.9%的外观泄漏。
英文摘要：
Localized 3D stylization aims to modify the appearance of a specified object part while preserving the remaining surfaces. In large reconstruction models (LRMs), this task is challenging because style is injected into intermediate appearance representations before rendering, while compact triplane features are shared across target and non-target surfaces, causing style leakage and boundary ambiguity. We propose Owner3D, a training-free framework for localized 3D stylization that integrates localized appearance control directly into the LRM reconstruction process. Specifically, Owner3D introduces ownership-guided style writing to restrict reference-style injection to target regions, producing a single localized stylized triplane without additional training while avoiding separate global style and appearance representations. To resolve appearance ambiguity near semantic boundaries, we further introduce boundary dual slots that maintain separate local feature sources for target and non-target regions. Finally, a surface-first texture readout hierarchically combines surface, 3D, and triplane ownership evidence to robustly recover appearance under incomplete visibility. Experiments on a benchmark constructed from Google Scanned Objects and PartNet demonstrate that Owner3D consistently outperforms existing 3D stylization methods in target-region style fidelity and non-target appearance preservation, reducing appearance leakage by 86.4% and 89.9% compared with StyleSplat and LAENeRF, respectively.
