# StyleSculptor: Zero-Shot Style-Controllable 3D Asset Generation with Texture-Geometry Dual Guidance

arXiv: https://arxiv.org/abs/2509.13301 · HTML: https://mlsanity.com/paper/2509.13301/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 13 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Builds on (most cited first, 12 of 12)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [TEXTure: Text-Guided Texturing of 3D Shapes](https://mlsanity.com/paper/2302.01721/) (2023)
- [Cross-Image Attention for Zero-Shot Appearance Transfer](https://mlsanity.com/paper/2311.03335/) (2023)
- [Neural Wavelet-domain Diffusion for 3D Shape Generation](https://mlsanity.com/paper/2209.08725/) (2022)
- [StyleGaussian: Instant 3D Style Transfer with Gaussian Splatting](https://mlsanity.com/paper/2403.07807/) (2024)
- [SPAGHETTI: Editing Implicit Shapes Through Part Aware Generation](https://mlsanity.com/paper/2201.13168/) (2022)
- [Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning](https://mlsanity.com/paper/2405.08054/) (2024)
- [Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images](https://mlsanity.com/paper/2406.13393/) (2024)
- [ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars](https://mlsanity.com/paper/2403.15383/) (2024)
- [StyleTex: Style Image-Guided Texture Generation for 3D Models](https://mlsanity.com/paper/2411.00399/) (2024)

## Built on by (most cited first, 8 of 8)

- [PEGAsus: 3D Personalization of Geometry and Appearance](https://mlsanity.com/paper/2602.08198/) (2026)
- [MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing](https://mlsanity.com/paper/2601.00204/) (2026)
- [UMI3D: Robust 3D Generation on Unconstrained Multi-Image Inputs via Simultaneous Focus Cross-Attention Routing](https://mlsanity.com/paper/2607.24298/) (2026)
- [HairLRM: Strand-based Hair Modeling via Large Reconstruction Models](https://mlsanity.com/paper/2606.15238/) (2026)
- [Loopy: Seamless Video Loop Generation via Anchored Looping Shift of Positional Embedding](https://mlsanity.com/paper/2608.23090/) (2026)
- [Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion](https://mlsanity.com/paper/2605.04412/) (2026)
- [OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylization](https://mlsanity.com/paper/2608.29905/) (2026)
- [DiDE:Direct Injection with Color-Texture DEcoupling for 3D Stylization](https://mlsanity.com/paper/2610.02044/) (2026)

## Abstract (arXiv)

Creating 3D assets that follow the texture and geometry style of existing ones is often desirable or even inevitable in practical applications like video gaming and virtual reality. While impressive progress has been made in generating 3D objects from text or images, creating style-controllable 3D assets remains a complex and challenging problem. In this work, we propose StyleSculptor, a novel training-free approach for generating style-guided 3D assets from a content image and one or more style images. Unlike previous works, StyleSculptor achieves style-guided 3D generation in a zero-shot manner, enabling fine-grained 3D style control that captures the texture, geometry, or both styles of user-provided style images. At the core of StyleSculptor is a novel Style Disentangled Attention (SD-Attn) module, which establishes a dynamic interaction between the input content image and style image for style-guided 3D asset generation via a cross-3D attention mechanism, enabling stable feature fusion and effective style-guided generation. To alleviate semantic content leakage, we also introduce a style-disentangled feature selection strategy within the SD-Attn module, which leverages the variance of 3D feature patches to disentangle style- and content-significant channels, allowing selective feature injection within the attention framework. With SD-Attn, the network can dynamically compute texture-, geometry-, or both-guided features to steer the 3D generation process. Built upon this, we further propose the Style Guided Control (SGC) mechanism, which enables exclusive geometry- or texture-only stylization, as well as adjustable style intensity control. Extensive experiments demonstrate that StyleSculptor outperforms existing baseline methods in producing high-fidelity 3D assets.