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

2025-09-16

AI Summary

This work addresses zero-shot, style-controllable 3D generation: given only a content image and one or more style reference images, it enables fine-grained, adjustable stylization of both texture and geometry. Methodologically, we propose a style-decoupled attention module and a style-guided control mechanism, integrating cross-3D attention, variance-driven channel-wise feature disentanglement, and dynamic feature fusion. To our knowledge, this is the first approach enabling *training-free*, independent stylization of texture and geometry, with continuous control over stylization intensity. Experiments demonstrate significant improvements over state-of-the-art baselines in both geometric fidelity and style alignment accuracy, while effectively suppressing semantic content leakage from the content image. The method is particularly suited for demanding 3D content creation scenarios—such as real-time gaming and VR—where precise, interpretable, and decoupled control over stylistic attributes is essential.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

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.

Problem

• Generating style-controllable 3D assets from content and style images
• Achieving zero-shot fine-grained texture and geometry style control
• Preventing semantic content leakage during style-guided 3D generation

Innovation

• Zero-shot style-controllable 3D generation
• Style Disentangled Attention module
• Texture-geometry dual guidance mechanism