SIC3D: Style Image Conditioned Text-to-3D Gaussian Splatting Generation
This work addresses the lack of controllability and texture ambiguity in text-to-3D generation by enabling style conditioning from images, benefiting users who need stylized 3D assets.
SIC3D introduces a two-stage pipeline for text-to-3D generation that first creates geometry from text and then transfers style from a reference image using a novel Variational Stylized Score Distillation loss, achieving improved geometric fidelity and style adherence over prior methods.
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.