Evaluating CrowdSplat: Perceived Level of Detail for Gaussian Crowds

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sun, Xiaohan, Xu, Yinghan, Dingliana, John, O'Sullivan, Carol
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913718180249600
author Sun, Xiaohan
Xu, Yinghan
Dingliana, John
O'Sullivan, Carol
author_facet Sun, Xiaohan
Xu, Yinghan
Dingliana, John
O'Sullivan, Carol
contents Efficient and realistic crowd rendering is an important element of many real-time graphics applications such as Virtual Reality (VR) and games. To this end, Levels of Detail (LOD) avatar representations such as polygonal meshes, image-based impostors, and point clouds have been proposed and evaluated. More recently, 3D Gaussian Splatting has been explored as a potential method for real-time crowd rendering. In this paper, we present a two-alternative forced choice (2AFC) experiment that aims to determine the perceived quality of 3D Gaussian avatars. Three factors were explored: Motion, LOD (i.e., #Gaussians), and the avatar height in Pixels (corresponding to the viewing distance). Participants viewed pairs of animated 3D Gaussian avatars and were tasked with choosing the most detailed one. Our findings can inform the optimization of LOD strategies in Gaussian-based crowd rendering, thereby helping to achieve efficient rendering while maintaining visual quality in real-time applications.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17085
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating CrowdSplat: Perceived Level of Detail for Gaussian Crowds
Sun, Xiaohan
Xu, Yinghan
Dingliana, John
O'Sullivan, Carol
Computer Vision and Pattern Recognition
Efficient and realistic crowd rendering is an important element of many real-time graphics applications such as Virtual Reality (VR) and games. To this end, Levels of Detail (LOD) avatar representations such as polygonal meshes, image-based impostors, and point clouds have been proposed and evaluated. More recently, 3D Gaussian Splatting has been explored as a potential method for real-time crowd rendering. In this paper, we present a two-alternative forced choice (2AFC) experiment that aims to determine the perceived quality of 3D Gaussian avatars. Three factors were explored: Motion, LOD (i.e., #Gaussians), and the avatar height in Pixels (corresponding to the viewing distance). Participants viewed pairs of animated 3D Gaussian avatars and were tasked with choosing the most detailed one. Our findings can inform the optimization of LOD strategies in Gaussian-based crowd rendering, thereby helping to achieve efficient rendering while maintaining visual quality in real-time applications.
title Evaluating CrowdSplat: Perceived Level of Detail for Gaussian Crowds
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.17085