SIC3D: Style Image Conditioned Text-to-3D Gaussian Splatting Generation
2026-04-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed SIC3D, a two-step method to create 3D objects from text and images. First, their model generates a 3D shape from a text description. Then, it applies the style of a reference image onto that 3D shape, improving texture detail and control. They introduced a new technique called Variational Stylized Score Distillation to better capture textures without messing up the shape. Their experiments showed that SIC3D produces more accurate shapes and styles than earlier methods.
text-to-3D generation3D Gaussian Splattingdiffusion modelsstyle transferVariational Stylized Score Distillationtexture synthesisgeometric fidelity3D representationregularizationimage-conditioned generation
Authors
Ming He, Zhixiang Chen, Steve Maddock
Abstract
Recent progress in text-to-3D object generation enables the synthesis of detailed geometry from text input by leveraging 2D diffusion models and differentiable 3D representations. However, the approaches often suffer from limited controllability and texture ambiguity due to the limitation of the text modality. To address this, we present SIC3D, a controllable image-conditioned text-to-3D generation pipeline with 3D Gaussian Splatting (3DGS). There are two stages in SIC3D. The first stage generates the 3D object content from text with a text-to-3DGS generation model. The second stage transfers style from a reference image to the 3DGS. Within this stylization stage, we introduce a novel Variational Stylized Score Distillation (VSSD) loss to effectively capture both global and local texture patterns while mitigating conflicts between geometry and appearance. A scaling regularization is further applied to prevent the emergence of artifacts and preserve the pattern from the style image. Extensive experiments demonstrate that SIC3D enhances geometric fidelity and style adherence, outperforming prior approaches in both qualitative and quantitative evaluations.