发表机构
University of Siegen（锡根大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
NRF-GS通过共享神经残差场替代逐溅射球谐函数，增强方向反射建模，在减少50%高斯数量的同时提升渲染质量与高频细节。
AI 中文摘要
我们重新审视了外观建模在3D高斯溅射（3DGS）中的作用，并表明视点相关反射的有限表达能力是表示冗余的关键驱动因素。在标准3DGS中，使用低阶球谐函数（SH），限制了溅射建模高频方向效应的能力，这通常通过增加溅射数量来补偿。我们提出了NRF-GS：用于高斯溅射的神经残差场，一种混合表示，用共享的神经残差场替代每个溅射的SH基。每个高斯编码一组紧凑的外观特征和朗伯基色，而一个轻量级的全局场景级MLP根据观察方向、距离和每个溅射的特征预测视点相关的残差。该公式通过将漫反射的逐溅射表示与用于高频细节的共享全局函数相结合，增强了方向反射建模，从而实现了更高的表达能力和跨溅射的参数共享。我们的关键见解是，通过准确捕获高频方向反射，特别是在镜面区域，GS表示变得更具表达性，减少了对几何冗余溅射的需求。因此，NRF-GS在减少多达50%的高斯数量的同时，实现了相当或更好的渲染质量，并产生了明显改进的镜面和高频细节。
英文摘要
We revisit the role of appearance modeling in 3D Gaussian Splatting (3DGS) and show that limited expressiveness in view-dependent reflectance is a key driver of representation redundancy. In standard 3DGS, low-order spherical harmonics (SH) are used, restricting the splats' ability to model high-frequency directional effects, which is typically compensated by increasing the number of splats. We propose \emph{NRF-GS: Neural Residual Fields for Gaussian Splatting}, a hybrid representation that replaces per-splat SH-bases with a shared neural residual field. Each Gaussian encodes a compact set of appearance features and a lambertian base color, while a lightweight \emph{global scene-level MLP} predicts view-dependent residuals conditioned on viewing direction, distance, and per-splat features. This formulation enhances directional reflectance modeling by combining diffuse per-splat reflectance representations with a shared global function for high-frequency details, enabling both higher expressiveness and parameter sharing across splats. Our key insight is that by accurately capturing high-frequency directional reflectance, especially in specular regions, the GS-representation becomes more expressive, reducing the need for geometrically redundant splats. As a result, NRF-GS achieves comparable or better rendering quality while reducing the number of Gaussians by up to 50\%, and produces visibly improved specular and high-frequency details.
CommentsAccepted at NeurIPS 2026
