RayGauss：基于体积高斯的射线投射用于真实感新视角合成
RayGauss: Volumetric Gaussian-Based Ray Casting for Photorealistic Novel View Synthesis
AI总结：
RayGauss提出用高斯函数结合球面高斯/谐波表示辐射场，并通过BVH加速的不规则高斯可微射线投射替代抛雪球，在Blender数据集上以25 FPS实现优于现有方法的渲染质量，同时避免伪影。
摘要：
基于可微体积渲染的方法在新视角合成方面取得了显著进展。一方面，创新方法已用局部参数化结构取代了神经辐射场（NeRF）网络，从而在合理时间内实现高质量渲染。另一方面，一些方法使用可微抛雪球（splatting）代替NeRF的射线投射，利用高斯核快速优化辐射场，从而能够精细地适应场景。然而，对不规则间隔核的可微射线投射研究甚少，而抛雪球方法尽管渲染速度快，却容易产生明显可见的伪影。我们的工作填补了这一空白，提出了发射辐射度c和密度σ的物理一致公式，将其分解为与球面高斯/球谐函数相关联的高斯函数，以实现全频段色度表示。我们还引入了一种方法，利用逐层积分辐射场并借助BVH结构的算法，实现对不规则分布高斯的可微射线投射。这使得我们的方法能够精细地适应场景，同时避免抛雪球伪影。因此，与最先进方法相比，我们实现了更优的渲染质量，同时保持了合理的训练时间，并在Blender数据集上达到了25 FPS的推理速度。项目主页（含视频和代码）：https://raygauss.github.io/
英文摘要：
Differentiable volumetric rendering-based methods made significant progress in novel view synthesis. On one hand, innovative methods have replaced the Neural Radiance Fields (NeRF) network with locally parameterized structures, enabling high-quality renderings in a reasonable time. On the other hand, approaches have used differentiable splatting instead of NeRF's ray casting to optimize radiance fields rapidly using Gaussian kernels, allowing for fine adaptation to the scene. However, differentiable ray casting of irregularly spaced kernels has been scarcely explored, while splatting, despite enabling fast rendering times, is susceptible to clearly visible artifacts. Our work closes this gap by providing a physically consistent formulation of the emitted radiance c and density σ, decomposed with Gaussian functions associated with Spherical Gaussians/Harmonics for all-frequency colorimetric representation. We also introduce a method enabling differentiable ray casting of irregularly distributed Gaussians using an algorithm that integrates radiance fields slab by slab and leverages a BVH structure. This allows our approach to finely adapt to the scene while avoiding splatting artifacts. As a result, we achieve superior rendering quality compared to the state-of-the-art while maintaining reasonable training times and achieving inference speeds of 25 FPS on the Blender dataset. Project page with videos and code: https://raygauss.github.io/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
