ConeGaussian：面向通用中心相机的抗锯齿高斯光线追踪

中文摘要 AI 辅助

在渲染中，相机是一个采样算子，将每个有限像素映射为一束光线。不同的相机模型会改变这束光线的几何形状，从而使统一且忠实的渲染公式变得具有挑战性。因此，高斯光线追踪通过其逆光线映射支持通用相机（具有光学中心），但通常将每个像素简化为一条中心光线。这忽略了与相机相关的像素足迹，在缩小（minification）时导致锯齿，而无约束的高斯在放大（magnification）时会暴露不支持的频率。我们提出了ConeGaussian，一个与相机模型无关的抗锯齿框架，用于基于高斯光线的渲染。ConeGaussian不是在特定相机的图像平面上定义像素滤波器，而是直接从相机原生逆映射产生的相邻光线构建各向异性足迹。我们在有限像素足迹的局部线性、深度局部、矩匹配近似下推导出闭式响应，同时相同的几何形状定义了每个高斯的训练频率下限。值得注意的是，通过构造，我们的滤波原理可以不加修改地用于经过标定的中心相机模型和多种高斯光线渲染骨干。此外，与mip-splatting不同，我们的场景空间频率下限和滤波使得在渲染时能够轻松合成，从而去除多余的模糊。在针孔和强畸变鱼眼采集上，ConeGaussian一致地改进了两种不同的基于光线的骨干，在1/8分辨率下最高提升4.3 dB，并将鱼眼LPIPS降低30%，而透视屏幕平面足迹公式在此类场景中不直接适用。

英文摘要

In rendering, a camera is a sampling operator that maps each finite pixel to a bundle of rays. Different camera models change the geometry of this bundle, thus making a unified and faithful rendering formulation challenging. Consequently, Gaussian ray tracing supports generic cameras (with optical center) through their inverse ray mappings, yet typically reduces every pixel to a single center ray. This ignores the camera-dependent pixel footprint, causing aliasing under minification, while unconstrained Gaussians expose unsupported frequencies under magnification. We present ConeGaussian, a camera-model-agnostic anti-aliasing framework for Gaussian ray-based rendering. Instead of defining the pixel filter on a camera-specific image plane, ConeGaussian constructs an anisotropic footprint directly from neighboring rays produced by the camera's native inverse mapping. We derive a closed-form response under a locally linear, depth-local, moment-matched approximation of the finite pixel footprint, while the same geometry defines a per-Gaussian training-frequency floor. Notably, by construction, our filtering principle can be used unmodified across calibrated central camera models and multiple Gaussian ray-rendering backbones. Additionally, unlike in mip-splatting, our scene-space frequency floor and filtering enable trivial composition at render time, allowing us to remove excess blurring. On pinhole and strongly distorted fisheye captures, ConeGaussian consistently improves two distinct ray-based backbones, by up to 4.3 dB at 1/8 resolution, and reduces fisheye LPIPS by 30% where perspective screen-plane footprint formulations are not directly applicable.

发表机构

• vivo Mobile Communication Co., Ltd., Shenzhen, China（维沃移动通信有限公司）

机构由 AI 辅助整理，请以论文原文为准。