StyleSplat：基于高斯泼溅的3D物体风格迁移
StyleSplat: 3D Object Style Transfer with Gaussian Splatting
AI总结：
针对现有3D风格迁移速度慢、难定位到特定物体的问题，提出轻量方法StyleSplat，基于3D高斯泼溅实现场景内多物体的定制化局部风格迁移，提升3D创作的可控性。
摘要：
辐射场领域的最新进展为创建高质量3D资产与场景开辟了新路径。风格迁移能够为这些3D资产赋予多样的艺术风格，革新创意表达形式。但现有技术通常速度较慢，或是无法将风格迁移定位到特定物体上。我们提出StyleSplat，这是一种轻量级方法，可针对由3D高斯表示的场景中的3D物体，参考风格图像完成风格化处理。我们的方法首先利用3D Gaussian splatting（高斯泼溅）学习场景的真实感表示，同时对单个3D物体进行分割。随后我们采用最近邻特征匹配损失微调所选物体的高斯参数，将其球谐系数与风格图像对齐，以保证一致性与视觉吸引力。StyleSplat支持快速、可定制的风格迁移，还能对场景内多个物体进行局部风格化，每个物体可采用不同风格。我们在多种3D场景与风格下验证了该方法的有效性，展现了其在3D创作中更强的可控性与定制化能力。
英文摘要：
Recent advancements in radiance fields have opened new avenues for creating high-quality 3D assets and scenes. Style transfer can enhance these 3D assets with diverse artistic styles, transforming creative expression. However, existing techniques are often slow or unable to localize style transfer to specific objects. We introduce StyleSplat, a lightweight method for stylizing 3D objects in scenes represented by 3D Gaussians from reference style images. Our approach first learns a photorealistic representation of the scene using 3D Gaussian splatting while jointly segmenting individual 3D objects. We then use a nearest-neighbor feature matching loss to finetune the Gaussians of the selected objects, aligning their spherical harmonic coefficients with the style image to ensure consistency and visual appeal. StyleSplat allows for quick, customizable style transfer and localized stylization of multiple objects within a scene, each with a different style. We demonstrate its effectiveness across various 3D scenes and styles, showcasing enhanced control and customization in 3D creation.
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。
