CrowdSplat: Exploring Gaussian Splatting For Crowd Rendering

TL;DR

CrowdSplat introduces a real-time crowd rendering method using 3D Gaussian Splatting, enabling high-quality, scalable, and memory-efficient visualization of animated crowds from monocular videos.

Contribution

It is the first to apply 3D Gaussian Splatting to crowd rendering, combining avatar reconstruction, crowd synthesis, and LoD optimization for real-time performance.

Findings

Achieves high-quality crowd rendering with efficient GPU memory usage.

Demonstrates real-time performance in dynamic crowd simulations.

Provides scalable solutions for diverse crowd visualization scenarios.

Abstract

We present CrowdSplat, a novel approach that leverages 3D Gaussian Splatting for real-time, high-quality crowd rendering. Our method utilizes 3D Gaussian functions to represent animated human characters in diverse poses and outfits, which are extracted from monocular videos. We integrate Level of Detail (LoD) rendering to optimize computational efficiency and quality. The CrowdSplat framework consists of two stages: (1) avatar reconstruction and (2) crowd synthesis. The framework is also optimized for GPU memory usage to enhance scalability. Quantitative and qualitative evaluations show that CrowdSplat achieves good levels of rendering quality, memory efficiency, and computational performance. Through the.se experiments, we demonstrate that CrowdSplat is a viable solution for dynamic, realistic crowd simulation in real-time applications.