SIC3D：基于风格图像的文本到3D高斯点云生成
SIC3D: Style Image Conditioned Text-to-3D Gaussian Splatting Generation
AI总结：
SIC3D通过引入变分风格化分数蒸馏损失，提升文本到3D生成的可控性和纹理精度，实验表明其在几何真实性和风格一致性上优于现有方法。
摘要：
近期文本到3D物体生成的进展通过利用2D扩散模型和可微3D表示实现了从文本输入合成详细几何结构。然而，现有方法受限于文本模态，存在可控性差和纹理模糊的问题。为此，我们提出SIC3D，一种可控的图像条件文本到3D生成管道，结合3D高斯点云（3DGS）。SIC3D分为两个阶段：第一阶段通过文本到3DGS生成模型生成3D物体内容；第二阶段将风格从参考图像转移到3DGS。在风格化阶段，我们引入了新颖的变分风格化分数蒸馏（VSSD）损失，以有效捕捉全局和局部纹理模式，同时缓解几何与外观之间的冲突。此外，进一步应用了缩放正则化以防止产生伪影并保留风格图像的模式。大量实验表明，SIC3D在几何真实性和风格一致性上得到提升，在定性和定量评估中均优于先前方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
