# SIC3D: Style Image Conditioned Text-to-3D Gaussian Splatting Generation

Source: [SIC3D: Style Image Conditioned Text-to-3D Gaussian Splatting Generation](<https://www.sota2.com/research/paper/69dc78947d0172140ec78b4d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-14T05:00:04.234Z

Authors: Ming He, Zhixiang Chen, Steve Maddock

Published: 2026-04-09T20:50:49.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Style Transfer on Masked renderings four fixed viewpoints](<https://www.sota2.com/research/sota/3d-style-transfer-on-masked-renderings-four-fixed-viewpoints.md>): 3D Style Transfer; Masked renderings four fixed viewpoints; NNFM: 0.151.

- [Stylized 3D Generation on 100 Prompt-Style Combinations (20 text prompts, 9 style images)](<https://www.sota2.com/research/sota/stylized-3d-generation-on-100-prompt-style-combinations-20-text-prompts-9-style-images.md>): Stylized 3D Generation; 100 Prompt-Style Combinations (20 text prompts, 9 style images); Object Quality (ELO): 1075.125.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.08760>)

[PDF](<https://arxiv.org/pdf/2604.08760.pdf>)