Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splatting

2026-01-31

AI Summary

Existing 3D style transfer methods struggle to flexibly balance content preservation and stylistic expression, limiting users’ ability to customize style intensity. To address this, we propose a novel intensity-controllable 3D style transfer framework that, for the first time, models style intensity using Gaussian neurons and introduces a learnable style modulator together with a cross-view alignment guidance mechanism. Built upon 3D Gaussian Splatting (3DGS) and diffusion models, our approach employs a two-stage optimization strategy that fuses full-style and style-free guidance signals to produce multi-view consistent stylized results. Experiments demonstrate that our method achieves superior visual quality and unprecedented controllability, enabling continuous adjustment of style intensity and significantly enhancing the customization capability of 3D style transfer.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

3D style transfer refers to the artistic stylization of 3D assets based on reference style images. Recently, 3DGS-based stylization methods have drawn considerable attention, primarily due to their markedly enhanced training and rendering speeds. However, a vital challenge for 3D style transfer is to strike a balance between the content and the patterns and colors of the style. Although the existing methods strive to achieve relatively balanced outcomes, the fixed-output paradigm struggles to adapt to the diverse content-style balance requirements from different users. In this work, we introduce a creative intensity-tunable 3D style transfer paradigm, dubbed \textbf{Tune-Your-Style}, which allows users to flexibly adjust the style intensity injected into the scene to match their desired content-style balance, thus enhancing the customizability of 3D style transfer. To achieve this goal, we first introduce Gaussian neurons to explicitly model the style intensity and parameterize a learnable style tuner to achieve intensity-tunable style injection. To facilitate the learning of tunable stylization, we further propose the tunable stylization guidance, which obtains multi-view consistent stylized views from diffusion models through cross-view style alignment, and then employs a two-stage optimization strategy to provide stable and efficient guidance by modulating the balance between full-style guidance from the stylized views and zero-style guidance from the initial rendering. Extensive experiments demonstrate that our method not only delivers visually appealing results, but also exhibits flexible customizability for 3D style transfer. Project page is available at https://zhao-yian.github.io/TuneStyle.

Problem

• 3D style transfer
• style intensity
• content-style balance
• customizability
• Gaussian Splatting

Innovation

• intensity-tunable style transfer
• Gaussian Splatting
• 3D stylization
• diffusion-based guidance
• style-content balance