GES：用于高效辐射场渲染的广义指数分层

摘要

3D 高斯飘零技术的进展显著加快了 3D 重建和生成的速度。然而，这可能需要大量的高斯函数，从而产生大量的内存占用。本文介绍了 GES（广义指数飘零），这是一种新颖的表示方法，采用广义指数函数（GEF）来建模 3D 场景，需要更少的粒子来表示一个场景，因此在效率上明显优于高斯飘零方法，并具有可插拔替换高斯基础工具的能力。GES 在理论上和实证上都得到验证，在基本的 1D 设置和逼真的 3D 场景中表现出色。它被证明更准确地表示具有清晰边缘的信号，这对于高斯函数来说通常是具有困难的，因为它们固有的低通特性。我们的实证分析表明，GEF 在拟合自然发生的信号（例如正方形、三角形和抛物线信号）方面优于高斯函数，从而减少了高斯飘零的内存占用增加所需的大量分割操作。通过频率调制损失的辅助，GES 在新视角合成基准测试中取得了竞争性能，同时只需要不到高斯飘零内存存储的一半，并且将渲染速度提高了多达 39%。代码可在项目网站 https://abdullahamdi.com/ges 上获得。

English

Advancements in 3D Gaussian Splatting have significantly accelerated 3D reconstruction and generation. However, it may require a large number of Gaussians, which creates a substantial memory footprint. This paper introduces GES (Generalized Exponential Splatting), a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes, requiring far fewer particles to represent a scene and thus significantly outperforming Gaussian Splatting methods in efficiency with a plug-and-play replacement ability for Gaussian-based utilities. GES is validated theoretically and empirically in both principled 1D setup and realistic 3D scenes. It is shown to represent signals with sharp edges more accurately, which are typically challenging for Gaussians due to their inherent low-pass characteristics. Our empirical analysis demonstrates that GEF outperforms Gaussians in fitting natural-occurring signals (e.g. squares, triangles, and parabolic signals), thereby reducing the need for extensive splitting operations that increase the memory footprint of Gaussian Splatting. With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks while requiring less than half the memory storage of Gaussian Splatting and increasing the rendering speed by up to 39%. The code is available on the project website https://abdullahamdi.com/ges .

GES：用于高效辐射场渲染的广义指数分层

GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering

摘要

Summary

Support

Support