Owner3D: Ownership-Guided Style Writing for Training-Free Localized 3D Stylization

Suchang Tao; Kaifeng Shi; Zhiyan Liu; Zhuoyuan Jiang; Yuqi Ouyang

cs.CVAug 14, 2026

Owner3D: Ownership-Guided Style Writing for Training-Free Localized 3D Stylization

Authors: Suchang Tao, Kaifeng Shi, Zhiyan Liu, Zhuoyuan Jiang, Yuqi Ouyang

Organizations: College of Computer Science, Sichuan University, Chengdu, China

Abstract

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.

Figures & tables

Figure 1: Representative localized 3D stylization results on real-world textured objects from Google Scanned Objects (GSO) [ 4 ] . Each example shows the source object, style reference image, and the stylized 3D output produced by Owner3D.

Figure 2: Our framework. Given a content image, a style image, and a target prompt, a frozen LRM first reconstructs the object to estimate surface, 3D, and triplane ownership. Ownership-guided style writing then localizes style injection during appearance decoding to produce a localized stylized triplane. Boundary dual slots provide separate target and preserve features near semantic boundaries, and surface-first texture readout hierarchically integrates ownership evidence to retrieve the appropriate appearance features for rendering.

Figure 3: Qualitative comparison on representative objects from the PartNet dataset. The figure compares Owner3D with 13 existing 3D and image-space stylization methods.

Gaussian-Splatting-Based 3D Stylization
Method	Style Fidelity $\downarrow$	T-Gram $\downarrow$	MV Cons. $\downarrow$	Leakage $\downarrow$	Runtime $\downarrow$
Owner3D (Ours)	0.1545	0.892	0.00009	0.0042	31.10s
StyleSplat [ 12 ]	0.4909	1.103	0.00010	0.0309	8.15min
StylizedGS [ 30 ]	0.2211	1.058	0.00020	0.0571	1.94min
G-Style [ 15 ]	0.6532	0.876	0.00029	0.0608	12.52min
NeRF-Based 3D Stylization

Table 1: Performance comparison on the PartNet dataset across different 3D and image-space stylization methods. T-Gram values are scaled by

10^{4}

. Best results are highlighted in bold. Slash marks indicate that leakage is not directly comparable for image-space methods because they preserve non-target pixels through per-view compositing.

Figure 4: Qualitative ablation study of Owner3D. Each variant removes one component to analyze its effect on style localization and boundary appearance preservation.

Variant	T-Gram $\downarrow$	Mean Non-Target Feature Drift $\downarrow$	Maximum Non-Target Feature Drift $\downarrow$
Full model	0.831	0.000	0.000
w/o surface ownership	0.839	0.007	0.015
w/o gated mixing	0.843	0.374	0.558
w/o style residual	0.950	0.133	0.293
w/o boundary dual slots	0.874	0.353	0.630
w/o owner priority	0.873	0.277	0.549

Table 2: Performance comparison of ablation variants on the GSO dataset. Each variant removes one component of Owner3D to evaluate its contribution. Non-target feature drift measures the VGG-feature deviation of preserved regions from the full model, where lower values indicate better non-target appearance preservation.

Figure 5: Routing and readout sensitivity on a representative GSO object under different minimum visible-view requirements $K_{\mathrm{vis}}$ .

Figure 6: Style-write sensitivity on a representative GSO object. Rows vary the style-write strength $\alpha$ , and columns vary the number of style-write layers. Increasing either parameter strengthens style transfer but progressively weakens content preservation.

Cell: T-Gram ( $\times 10^{4}$ ) $\downarrow$ / Style Fidelity $\downarrow$ / Content SSIM $\uparrow$
α Layers	2	6	8
0.10	0.81 / 0.212 / 0.998	0.81 / 0.211 / 0.993	0.81 / 0.211 / 0.988
0.35	0.79 / 0.199 / 0.986	0.79 / 0.189 / 0.940	0.79 / 0.190 / 0.921
0.65	0.75 / 0.181 / 0.955	0.72 / 0.132 / 0.813	0.74 / 0.135 / 0.804
0.90	0.71 / 0.166 / 0.917	0.60 / 0.079 / 0.751	0.63 / 0.113 / 0.740
1.20	0.65 / 0.144 / 0.858	0.52 / 0.066 / 0.714	0.55 / 0.100 / 0.706

Table 3: Two-dimensional style-write sensitivity. Bold indicates the best value for each metric; red marks the selected operating point.

Tri-Plane Representations

See all 8 papers

AnyStyle: Single-Pass Multimodal Stylization for 3D Gaussian Splatting
Feb 3, 2026Joanna Kaleta, Bartosz Świrta, Kacper Kania +33D Gaussian Splatting Feed-Forward 3D Reconstruction
Warsaw University of Technology · Sano Centre for Computational Medicine · IDEAS NCBR +2
InStyle: Instant Appearance Stylization of 3D Shapes
Dec 3, 2025Melis Ocal, Xiaoyan Xing, Yue Li +33D Shape Editing 3D Representation Learning
University of Amsterdam · Bosch Center for AI
DiDE:Direct Injection with Color-Texture DEcoupling for 3D Stylization
Oct 1, 2026Tao Wu, Alexandra Gomez-Villa, Senmao Li +3
Computer Vision Center, Universitat Autònoma de Barcelona, Spain · Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates · Jilin University, China +2

Feb 3, 2026J/K move · Enter open · S save

AnyStyle: Single-Pass Multimodal Stylization for 3D Gaussian Splatting

Joanna Kaleta, Bartosz Świrta, Kacper Kania, Tomasz Trzciński+2

Warsaw University of Technology · Sano Centre for Computational Medicine · IDEAS NCBR+2

3D Gaussian Splatting Feed-Forward 3D Reconstruction

Open paper AskPDF arXiv

The growing demand for rapid and scalable 3D asset creation has driven interest in feed-forward 3D reconstruction methods, with 3D Gaussian Splatting (3DGS) emerging as an effective scene representation. While recent approaches have demonstrated pose-free reconstruction from unposed image collections, integrating stylization or appearance control into such pipelines remains underexplored. Existing attempts largely rely on image-based conditioning, which limits both controllability and flexibility. In this work, we introduce AnyStyle, a feed-forward 3D reconstruction and stylization framework that enables pose-free, zero-shot stylization through multimodal conditioning. Our method supports both textual and visual style inputs, allowing users to control the scene appearance using natural language descriptions or reference images. We propose a modular stylization architecture that requires only minimal architectural modifications and can be integrated into existing feed-forward 3D reconstruction backbones. Experiments demonstrate that AnyStyle improves style controllability over prior feed-forward stylization methods while preserving high-quality geometric reconstruction. A user study further confirms that AnyStyle achieves superior stylization quality compared to an existing state-of-the-art approach. Repository: https://github.com/joaxkal/AnyStyle.

Abstract

Tri-Plane Representations

Explore similar work

AnyStyle: Single-Pass Multimodal Stylization for 3D Gaussian Splatting

InStyle: Instant Appearance Stylization of 3D Shapes

DiDE:Direct Injection with Color-Texture DEcoupling for 3D Stylization