CrowdSplat: Exploring Gaussian Splatting For Crowd Rendering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Xiaohan, Xu, Yinghan, Dingliana, John, O'Sullivan, Carol
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917129709682688
author Sun, Xiaohan
Xu, Yinghan
Dingliana, John
O'Sullivan, Carol
author_facet Sun, Xiaohan
Xu, Yinghan
Dingliana, John
O'Sullivan, Carol
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17792
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CrowdSplat: Exploring Gaussian Splatting For Crowd Rendering
Sun, Xiaohan
Xu, Yinghan
Dingliana, John
O'Sullivan, Carol
Computer Vision and Pattern Recognition
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.
title CrowdSplat: Exploring Gaussian Splatting For Crowd Rendering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.17792