用傅里叶编码实现可缩放的辐射场渲染，支持实时多级细节控制。
Fourier Splatting: Generalized Fourier encoded primitives for scalable radiance fields
- 用傅里叶编码参数化平面微表面，构建可动态调整精度的渲染原语。
- 同一模型通过截断系数即可在不同细节层级渲染，无需重新训练。
- 适合带宽受限场景，兼顾质量与效率，适用于实时渲染应用。
新视角合成近年来因3D高斯点阵（3DGS）而革新，其通过显式原语光栅化实现实时渲染。然而现有方法将视觉保真度严格绑定于原语数量：降质仅能通过裁剪原语实现。本文提出首个固有可扩展的辐射场渲染原语。傅里叶点阵采用傅里叶编码描述符参数化任意闭合形状的平面微表面，使单一训练模型可通过运行时截断傅里叶系数实现不同细节层级的渲染。为保障优化稳定，我们引入跨边界梯度扩展的直通估计器，并提出HYDRA策略，在马尔可夫链蒙特卡洛框架内将复杂原语分解为更简单成分。本方法在平面原语框架中达到最优渲染质量，且在标准基准上与领先体素表示相当的感知指标，为带宽受限下的高保真渲染提供通用解决方案。
原文摘要 · Abstract (English)
Novel view synthesis has recently been revolutionized by 3D Gaussian Splatting (3DGS), which enables real-time rendering through explicit primitive rasterization. However, existing methods tie visual fidelity strictly to the number of primitives: quality downscaling is achieved only through pruning primitives. We propose the first inherently scalable primitive for radiance field rendering. Fourier Splatting employs scalable primitives with arbitrary closed shapes obtained by parameterizing planar surfels with Fourier encoded descriptors. This formulation allows a single trained model to be rendered at varying levels of detail simply by truncating Fourier coefficients at runtime. To facilitate stable optimization, we employ a straight-through estimator for gradient extension beyond the primitive boundary, and introduce HYDRA, a densification strategy that decomposes complex primitives into simpler constituents within the MCMC framework. Our method achieves state-of-the-art rendering quality among planar-primitive frameworks and comparable perceptual metrics compared to leading volumetric representations on standard benchmarks, providing a versatile solution for bandwidth-constrained high-fidelity rendering.
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。