发表机构
KAIST AI（韩国科学技术院人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
VolS-GS提出一种可重照明高斯溅射框架，利用体积次表面散射输运求解器，在OLAT捕获下重建物体并提升新光照和视角下的渲染质量。
AI 中文摘要
我们提出了VolS-GS，一个可重照明的高斯溅射框架，它从一次一光（OLAT）捕获中重建物体，并在新颖的光照和视角下渲染它们。可重照明的高斯溅射方法通常在每个图元上独立地建模外观，这使得非局部效应难以表示。这种限制在次表面散射中尤为明显，其中光在物体一个位置进入可以在另一个位置出射。我们不是仅用神经网络或每个图元上的局部核来建模这种效应，而是利用高斯场景的空间支撑作为可微有限体积输运求解器的域，使得光可以在物体内部传播。一个小型网络预测每个高斯的散射和吸收系数，求解器通过所得场重新分配入射光。系数是拟合到图像而不是测量的，因此求解器提供了用于聚合每个图元外观的输运形状路径，而不是材料的测量。为了防止学习到的阴影和镜面项接管其他组件，我们的阴影项由可见性连同透射率和求解器产生的散射一起预测，并且一个正则化器在阴影项预测为未照亮的区域抑制镜面高光。在三个OLAT基准上的实验表明，VolS-GS在保留光照和视图上持续提高了重照明质量。
英文摘要
We present VolS-GS, a relightable Gaussian splatting framework that reconstructs objects from one-light-at-a-time (OLAT) captures and renders them under novel lighting and viewpoints. Relightable Gaussian Splatting methods typically model appearance independently at each primitive, which makes non-local effects difficult to represent. This limitation is particularly apparent for subsurface scattering, where light entering the object at one location can emerge at another. Rather than modeling this effect solely with a neural network or a local kernel at each primitive, we use the spatial support of the Gaussian scene as the domain of a differentiable finite-volume transport solver, so that light can propagate through the object's interior. A small network predicts scattering and absorption coefficients for each Gaussian, and the solve redistributes incident light through the resulting field. The coefficients are fit to images rather than measured, so the solve supplies a transport-shaped path for aggregating per-primitive appearance, not a measurement of the material. To keep the learned shadow and specular terms from taking over the other components, our shadow term is predicted from visibility together with the transmittances and the scattering the solve produces, and a regularizer suppresses specular highlights in regions the shadow term predicts to be unlit. Experiments on three OLAT benchmarks show that VolS-GS consistently improves relighting quality on held-out lights and views.
Comments23 pages
