CrowdSplat: Exploring Gaussian Splatting For Crowd Rendering

Xiaohan Sun, Yinghan Xu, John Dingliana, Carol O'Sullivan
1/29/2025
cs.CV

No official code found. Best implementation: RockyXu66/CrowdSplat (3 stars, MIT, last commit 2025-03-06).

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.

View on arXivView PDF

Code Implementations(1)

RockyXu66/CrowdSplatCommunity100%
MIT
30GLSL, PythonJun 4, 20241 years agoMIT

Similar Papers

Evaluating CrowdSplat: Perceived Level of Detail for Gaussian Crowds

88% match2025

2DGS-Avatar: Animatable High-fidelity Clothed Avatar via 2D Gaussian Splatting

85% match2025

GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh

85% match1 repo1282024

MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars

85% match1 repo432025

HGC-Avatar: Hierarchical Gaussian Compression for Streamable Dynamic 3D Avatars

84% match2025

From Far and Near: Perceptual Evaluation of Crowd Representations Across Levels of Detail

84% match2025

Cite this paper

@article{sun2025crowdsplat,
  title  = {CrowdSplat: Exploring Gaussian Splatting For Crowd Rendering},
  author = {Xiaohan Sun and Yinghan Xu and John Dingliana and Carol O'Sullivan},
  year   = {2025},
  eprint = {2501.17792},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.17792v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.17792.svg)](https://codeofpaper.com/paper/2501.17792)

Discussion