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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Xiaohan, O'Sullivan, Carol
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908901124866048
author Sun, Xiaohan
O'Sullivan, Carol
author_facet Sun, Xiaohan
O'Sullivan, Carol
contents In this paper, we investigate how users perceive the visual quality of crowd character representations at different levels of detail (LoD) and viewing distances. Each representation, including geometric meshes, image-based impostors, Neural Radiance Fields (NeRFs), and 3D Gaussians, exhibits distinct trade-offs between visual fidelity and computational performance. Our qualitative and quantitative results provide insights to guide the design of perceptually optimized LoD strategies for crowd rendering.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20558
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Far and Near: Perceptual Evaluation of Crowd Representations Across Levels of Detail
Sun, Xiaohan
O'Sullivan, Carol
Computer Vision and Pattern Recognition
Graphics
Human-Computer Interaction
In this paper, we investigate how users perceive the visual quality of crowd character representations at different levels of detail (LoD) and viewing distances. Each representation, including geometric meshes, image-based impostors, Neural Radiance Fields (NeRFs), and 3D Gaussians, exhibits distinct trade-offs between visual fidelity and computational performance. Our qualitative and quantitative results provide insights to guide the design of perceptually optimized LoD strategies for crowd rendering.
title From Far and Near: Perceptual Evaluation of Crowd Representations Across Levels of Detail
topic Computer Vision and Pattern Recognition
Graphics
Human-Computer Interaction
url https://arxiv.org/abs/2510.20558