将图像分解技术扩展到3D高斯点云，实现对物体纹理的精准编辑。
Intrinsic decomposition and editing of 3D Gaussian splats
- 将漫反射材质与光照分离为独立高斯点集，适配不同层级特征。
- 基于数据驱动预测优化多视角图像分解，提升解耦精度。
- 仅改一张图的材质即可全局重渲染，适合3D内容创作者使用。
固有分解将图像颜色表示为漫反射反照率与阴影的乘积，可能还包含视角依赖残差，长期以来在图像编辑中用于修改物体颜色和纹理而不影响光照。本文将固有分解扩展至高斯点云表示的辐射场，提出解决三个关键问题的方案：首先，描述如何将固有分解建模为独立的高斯原始集合，使每组能适应其所代表层的特性；其次，提出一种由数据驱动预测引导的优化过程，将多视角场景照片分解为上述固有集合；最后，提供一种编辑工作流，用户只需在单张图像中修改平面表面的反照率，即可捕捉该编辑并重建具有合理光照的全场景辐射场，支持任意视角重渲染。
原文摘要 · Abstract (English)
Intrinsic decomposition which expresses image colors as the product of diffuse albedo and shading, possibly augmented with view-dependent residuals has a long history in image editing as it enables the modification of object colors and textures without altering lighting. We extend intrinsic decomposition to radiance fields represented with Gaussian splatting by proposing solutions to three key aspects of such decomposition. First, we describe how to model the intrinsic decomposition as independent sets of Gaussian primitives, which allows each set to adapt to the characteristics of the layer it represents. Second, we present an optimization procedure guided by data-driven predictions to disentangle multi-view photographs of a scene into the aforementioned intrinsic sets. Finally, we provide an editing workflow where users modify the texture of planar surfaces simply by modifying the albedo of that surface in one image. Capturing this edit within the intrinsic radiance field allows re-rendering of the edited scene with plausible lighting under arbitrary viewpoints.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。