InStyle: Instant Appearance Stylization of 3D Shapes

Melis Ocal; Xiaoyan Xing; Yue Li; Ngo Anh Vien; Sezer Karaoglu; Theo Gevers

cs.CVDec 3, 2025

InStyle: Instant Appearance Stylization of 3D Shapes

Authors: Melis Ocal, Xiaoyan Xing, Yue Li, Ngo Anh Vien, Sezer Karaoglu, Theo Gevers

Organizations: University of Amsterdam · Bosch Center for AI

Abstract

3D stylization is central to game development, virtual reality, and digital arts, where the demand for diverse assets calls for scalable methods that support fast, high-fidelity manipulation. Existing text-to-3D stylization methods typically distill from 2D image editors, requiring time-intensive per-asset optimization and exhibiting multi-view inconsistency due to the limitations of current text-to-image models, which makes them impractical for large-scale production. In this paper, we introduce GaussianBlender, a pioneering feed-forward framework for text-driven 3D stylization that performs edits instantly at inference. Our method learns structured, disentangled latent spaces with controlled information sharing for geometry and appearance from spatially-grouped 3D Gaussians. A latent diffusion model then applies text-conditioned edits on these learned representations. Comprehensive evaluations show that GaussianBlender not only delivers instant, high-fidelity, geometry-preserving, multi-view consistent stylization, but also surpasses methods that require per-instance test-time optimization - unlocking practical, democratized 3D stylization at scale.

Figures & tables

Figure 1 : Given a 3D Gaussian splat asset and an edit prompt, InStyle - a diffusion-based feed-forward style editor - delivers geometry-preserving, multi-view-consistent appearance stylization with a single-pass inference (0.26 s per asset), without per-asset test-time optimization. InStyle enables (a) library-scale stylization across diverse assets and (b) interactive, user-driven customization, (c) while generalizing to real-world captures - unlocking practical, democratized 3D stylization at scale.

Figure 2 : Overview of our method. (1) Latent space learning: Given input Gaussians, our method first groups them based on spatial proximity and encodes into group-structured disentangled latent spaces, with controlled cross-branch feature-sharing. (2) Latent diffusion pre-training: A denoiser $d_{\varrho}$ then learns to denoise the noisy appearance latent ${\mathbf{z}_{c}^{s}}_{\mathbf{t}}$ conditioned on text embedding $\mathcal{C}$ . (3) Latent editing: Once 3D priors are captured, $d_{\varrho}$ is further trained to learn an editing function $g(\cdot)$ that maps latent $\mathbf{z}_{c}^{s}$ to a modified latent $\mathbf{z}_{c}^{e}$ based on text embedding $\mathcal{C}^{e}$ , guided by the geometry latent ${\mathbf{z}_{g}^{s}}$ . At inference , InStyle generates modified high-quality, 3D-consistent assets from text prompts in a single feed-forward pass instantly, fully eliminating test-time optimization. Trainable models at each stage are denoted.

Figure 3 : Qualitative comparison with state-of-the-art methods. Baselines often produce over-saturated, dramatic stylizations that distort 3D structure ( e.g . , blurred boundaries; rows 2,3,5, col. 4), minimal edits that are barely perceptible (row 2, col. 2,3), or severe geometric artifacts. In contrast, InStyle delivers high-fidelity, text-aligned 3D stylizations with strong geometry preservation in a single feed-forward pass.

Figure 4 : Cross-dataset generalization on OmniObject3D [ 74 ] . Our framework demonstrates strong style editing performance on out-of-distribution 3D assets.

Figure 5 : Generalization to complex real-world scenes from SceneSplat [ 36 ] . Using a simple extract-edit-reinsert pipeline, InStyle produces coherent stylizations despite capture artifacts, clutter, and occlusions.

Method	Text Alignment $\uparrow$	Structural Consistency $\uparrow$	Visual Quality $\uparrow$
IN2N	16.30%	20.24%	21.68%
IGS2GS	14.67%	17.48%	20.21%
GaussCtrl	20.10%	15.84%	17.48%
GaussianEditor	15.21%	4.37%	6.01%
Ours	33.69%	42.05%	34.60%

Table 2 : User study results. InStyle is consistently preferred over the baselines across the three criteria.

	LightGaussian	Input 3DGS	w/o disent.	w/ disent. (Ours)
PSNR $\uparrow$	35.2117	32.7136	33.6635	34.3299

Table 3 : Effect of disentanglement on 3DGS parameter reconstruction. LightGaussian: original LightGaussian [ 17 ] reconstruction; Input 3DGS : downsampled LightGaussian 3DGS used as our model input; w/o disent. : single-branch variant; w/ disent. : dual-branch Gaussian VAE.

Figure 6 : Visual assessment of Gaussian VAE reconstructions. The proposed dual-branch Gaussian VAE yields sharper reconstructions with better geometric fidelity and color accuracy.

	$\mathrm{CLIP}_{\mathrm{sim}}\!\uparrow$	$\mathrm{CLIP}_{\mathrm{dir}}\!\uparrow$
(1) w/o $\mathcal{L}_{LD}$	0.227	0.183
(2) w/o feat. sharing	0.221	0.171
(3) Ours (full)	0.260	0.223

Table 4 : Assessment of framework components. We report

\mathrm{CLIP}_{\mathrm{sim}}\!\uparrow

and

\mathrm{CLIP}_{\mathrm{dir}}\!\uparrow

to compare different variants.

Figure 7 : Effect of style catalog size. InStyle maintains stylization performance as the style catalog size grows from 1 to 30.

Figure 8 : Application. (a) Interactive scene editing: InStyle can be adopted for interactive object-level scene editing. (b) Style transfer via appearance-latent exchange: Transferring the appearance code from a source to a target asset modifies appearance while preserving the geometric structure.

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Evaluation Benchmark	“Make its colours look like rainbow”, “Make it Starry Night Van Gogh painting style”, “Make it wooden”, “Make it in cyberpunk style”, “Make it pop art neon duotone”, “Make it marble”, “Make it Barbie style”, “Make it golden”, “Make it botanical themed”, “Make it Halloween themed”
Training (single-prompt)	Each prompt in the evaluation benchmark is used to train a separate model.
Training (multi-prompt)	“Make its colours look like rainbow”, “Make it Starry Night Van Gogh painting style”, “Make it wooden”, “Make it in cyberpunk style”, “Make it pop art neon duotone”, “Make it marble”, “Make it Barbie style”, “Make it golden”, “Make it botanical themed”, “Make it Halloween themed”, “Make it Hello Kitty themed”, “Make it look like made of steel”, “Make it The Scream Edvard Munch painting”, “Make it in sunset palette”, “Make it Pirates of the Caribbean style”, “Make it look like a statue”, “Make it Garfield themed”, “Make it look like made of bronze”, “Make it Dalmatian style”, "Make it gothic style", "Make it ocean palette", "Make it graffiti street art style", “Make it watercolor painting style”, "Turn it into red", “Turn it into orange”, "Turn it into pink", "Turn it into blue", "Turn it into yellow", "Turn it into green", "Turn it into black"

Appendix

Table 5 : Edit prompts used in the evaluation benchmark and for training the single-prompt and multi-prompt models.

Criterion
Text Alignment	Which stylized result follows the prompt most closely? Consider whether the style change is too subtle (almost no visible change), or too drastic (over-saturated).
Structural Consistency	Which edited result best preserves the original asset’s 3D structure while applying only the requested appearance stylization? The object’s shape should not change after stylization (e.g., no changes to the object’s physical structure; for characters, the face, identity and features, must remain unchanged).
Visual Quality	Which edited result looks best overall?

Appendix

Table 6 : The criteria used in the user study. The definitions listed here are also provided to participants.

Figure 9 : Visual results of expanding the style catalog. InStyle maintains high-quality 3D stylization and geometry preservation as the number of training prompts increases.

Figure 10 : Additional visual results of our method. InStyle delivers instant, geometry-preserving, and multi-view-consistent 3D stylizations in a single feed-forward pass.

Figure 11 : Additional visual results of our method. InStyle delivers instant, geometry-preserving, and multi-view-consistent 3D stylizations in a single feed-forward pass.

	$\mathrm{CLIP}_{\mathrm{sim}}\!\uparrow$	$\mathrm{CLIP}_{\mathrm{dir}}\!\uparrow$	Structure Dist. $\downarrow$
MV-L1	0.251	0.210	0.0064
DMD + MV-L1 (Ours)	0.260	0.223	0.0050

Appendix

Table 7 : Effect of DMD over MV-L1 Supervision. DMD improves metrics over MV-L1 supervision.

Figure 12 : Effect of DMD over MV-L1 Supervision. Compared with the MV-L1 baseline, adding the DMD objective yields sharper, more vivid stylization results.

	$\mathrm{CLIP}_{\mathrm{sim}}\!\uparrow$	$\mathrm{CLIP}_{\mathrm{dir}}\!\uparrow$	Structure Dist. $\downarrow$
(1) $s_{T}\!\in\![5.5,9.5]$	0.260	0.223	0.0050
(2) $s_{T}\!\in\![9.5,12.5]$	0.263	0.226	0.0089
(3) $s_{T}\!\in\![12.5,15.5]$	0.268	0.232	0.0172

Appendix

Table 8 : Effect of guidance scale. Higher text guidance scales yield improved CLIP metrics with minimal loss in structural consistency.

Figure 13 : Latent perturbation and appearance swapping. Perturbations affect the corresponding appearance or geometry factor, while appearance swaps transfer appearance while preserving geometry.

Figure 14 : Failure cases. Our model struggles to represent complex scenes with fine-grained details using 16384 Gaussians, leading to lower-quality results. This can be addressed by increasing the number of Gaussians to better capture such details.

Explore similar work

AnyStyle: Single-Pass Multimodal Stylization for 3D Gaussian Splatting
Feb 3, 2026Joanna Kaleta, Bartosz Świrta, Kacper Kania +3Stylization 3D Generative Models
Warsaw University of Technology · Sano Centre for Computational Medicine · IDEAS NCBR +2
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
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

Feb 3, 2026, cs.CVJ/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

Stylization 3D Generative Models 3D Assets 3D Generation Style

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

Explore similar work

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

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

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