BiGS：用于可重光照3D高斯泼溅的双向高斯基元
BiGS: Bidirectional Gaussian Primitives for Relightable 3D Gaussian Splatting
AI总结：
提出双向高斯基元，通过将光本征分解集成至Gaussian splatting框架，采用双向球谐函数统一表面与体积材质散射表示，实现无需法线的3D对象实时重光照。
摘要：
我们提出双向高斯基元，这是一种基于图像的新视角合成技术，旨在表示和渲染动态光照下具有表面和体积材质的3D对象。该方法将光本征分解集成到Gaussian splatting框架中，实现3D对象的实时重光照。为在统一外观模型中结合表面与体积材质，我们采用基于双向球谐函数的依赖光和视角的散射表示。该模型不使用特定的与表面法线相关的反射函数，使其更兼容Gaussian splatting等法线未定义的体积表示。我们通过重建和渲染复杂材质对象验证了该方法。使用One-Light-At-a-Time (OLAT)数据作为输入，能在新光照条件下实时重现逼真外观。
英文摘要：
We present Bidirectional Gaussian Primitives, an image-based novel view synthesis technique designed to represent and render 3D objects with surface and volumetric materials under dynamic illumination. Our approach integrates light intrinsic decomposition into the Gaussian splatting framework, enabling real-time relighting of 3D objects. To unify surface and volumetric material within a cohesive appearance model, we adopt a light- and view-dependent scattering representation via bidirectional spherical harmonics. Our model does not use a specific surface normal-related reflectance function, making it more compatible with volumetric representations like Gaussian splatting, where the normals are undefined. We demonstrate our method by reconstructing and rendering objects with complex materials. Using One-Light-At-a-Time (OLAT) data as input, we can reproduce photorealistic appearances under novel lighting conditions in real time.
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。
