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

Tao Wu; Alexandra Gomez-Villa; Senmao Li; Yaxing Wang; Joost van de Weijer; Kai Wang

cs.CVOct 1, 2026

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

Authors: Tao Wu, Alexandra Gomez-Villa, Senmao Li, Yaxing Wang, Joost van de Weijer, Kai Wang

Organizations: Computer Vision Center, Universitat Autònoma de Barcelona, Spain · Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates · Jilin University, China · City University of Hong Kong (Dongguan), China

Abstract

Recent advances in rectified flow-based image-to-3D generative models have enabled high-fidelity 3D asset generation. Building on this, a growing line of work has exploited these strong 3D priors for training-free stylization, transferring visual attributes from a reference image onto a generated 3D asset. However, existing methods enforce an all-or-nothing paradigm: color and texture are transferred jointly, with no mechanism to control them independently -- a limitation we formalize as Disentangled 3D Stylization(Disen3D). To address this, we propose DiDE, the first training-free framework for Disen3D. Key to our approach is the observation that the structured latent space of image-to-3D models is overcomplete with respect to texture: texture information occupies only a small subset of the style-significant channels, leaving a free subspace available for independent color encoding. DiDE exploits this via a channel partition mechanism that processes a content image, a texture reference, and a color reference through dedicated branches and composes both style signals interference-free at every self-attention layer, preserving content geometry throughout. Experiments on Disen3D-Bench, our newly collected multi-reference benchmark, show that DiDE consistently outperforms 2D and 3D stylization baselines in color fidelity, texture transfer, and content preservation.

Figures & tables

Figure 1 : Our training-free framework DiDE enables the generation of stylized 3D assets, with flexible control over the independent modulation of color or texture.

Figure 4 : Overview of DiDE . Left: Our framework takes three inputs — a content image, a texture reference, and a color reference — processed through three independent branches: the content branch ( blue ), the texture branch ( red ), and the color branch ( green ). Right: At each DiT block, the texture and color branches produce independent self-attention outputs. A channel selection operator $\mathcal{S}$ partitions the feature channels into texture-allocated (high-variance) and color-allocated (low-variance) subsets, and the two attention outputs are composed via the binary mask $\mathbf{M_{c}}$ into a single fused representation $\mathbf{SA}_{\text{fusion}}$ , which is then injected into the residual stream of the content branch through its gated update.

Figure 5 : Comparison with existing 3D stylization methods and adapted baselines for the Disen3D problem. The first two rows show results with a single style reference, while the remaining rows show results with disentangled texture and color references.

Method	CLIP-I $\uparrow$	Geometry		Color			Texture
Method	CLIP-I $\uparrow$	CD ${}_{{}^{\times 10^{2}}}$ $\downarrow$	HD ${}_{{}^{\times 10^{2}}}$ $\downarrow$	MS-SWD $\downarrow$	C-Hist $\downarrow$	VLM $\uparrow$	LPIPS $\downarrow$	SSIM ${}_{{}^{\times 10^{3}}}$ $\uparrow$	VLM $\uparrow$
SADis Qin et al. (2025)	0.73	18.17	41.59	18.38	0.99	37.17	0.65	116.10	18.00
StyleSculptor Qu et al. (2025)	0.74	17.91	8.38	21.26	0.89	35.44	0.69	124.61	23.22
MorphAny3D Sun et al. (2026)	0.71	198.52	44.50	18.31	0.91	40.05	0.65	117.21	19.72
DiDE (Ours)	0.75	15.38	7.87	20.40	0.87	70.94	0.68	125.19	30.72

Table 1 : Quantitative comparisons with existing style transfer methods. The best and second-best results are highlighted in bold and underlined , respectively. CD and HD denote Chamfer Distance and Hausdorff Distance, respectively.

Figure 6 : Ablation on grayscale conversion and Voronoi tessellation preprocessing.

Figure 7 : DiDE applied to the TRELLIS.2 backbone, showing generalization across model variants.

Figure 8 : Ablation on channel selection variance source: texture vs. color branch.

$\lambda$	Color		Texture
$\lambda$	MS-SWD $\downarrow$	C-Hist $\downarrow$	LPIPS $\downarrow$	SSIM ${}_{{}^{\times 10^{3}}}$ $\uparrow$
0.5	20.24	0.92	0.68	83.36
1.0	19.47	0.89	0.69	83.34
1.2	19.25	0.89	0.69	83.45
1.5	19.32	0.90	0.70	83.30
2.0	19.38	0.90	0.70	83.40

Table 2 : Ablation on color branch weight

\lambda

Method	Geometry $\uparrow$	Texture $\uparrow$	Color $\uparrow$
MorphAny3D	4.4%	1.2%	2.3%
SADiS	12.1%	3.2%	8.7%
StyleSculptor	31.8%	37.4%	16.6%
Ours	51.7%	58.2%	72.4%

Table 3: User study results on geometry, texture, and color preference. Higher is better.

Figure 9 : Failure case under texture-reference brightness shifts.

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 12 : Additional qualitative comparisons

Figure 13 : DINOv2 cosine similarity between rendered outputs and texture references as a function of the number of PCA components retained from TRELLIS texture-significant features. Similarity stabilizes after as few as 10 components, confirming the low intrinsic dimensionality of texture within the feature space.

Explore similar work

DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement
Jul 27, 2026Kai Wang, Ziheng Ouyang, Xuying Zhang +23D Assets Fidelity
VCIP, Nankai University Tianjin, China · Zhongguancun Academy Beijing, China · Joy Future Academy, JD Beijing, China +1
Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion
May 6, 2026Yiran Qiao, Yiren Lu, Yunlai Zhou +5High-Fidelity 3D Generation Photorealistic Style Transfer
Case Western Reserve University
OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylization
Aug 30, 2026Tomohiro Aizawa, Shigeru Kuriyama, Chunzhi Gu3D Assets Stylization
University of Fukui, Japan · Toyohashi University of Technology, Japan · AI Lab, CyberAgent, Inc., Japan

Jul 27, 2026, cs.CVJ/K move · Enter open · S save

DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement

Kai Wang, Ziheng Ouyang, Xuying Zhang, Ming-Ming Cheng+1

VCIP, Nankai University Tianjin, China · Zhongguancun Academy Beijing, China · Joy Future Academy, JD Beijing, China+1

3D Assets Fidelity

Open paper AskPDF arXiv

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.

Abstract

Explore similar work

DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement

Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion

OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylization