paperbot · PL 论文追踪

全部论文 待读 收藏

P2 How Developers Optimize Virtual Reality Applications: A Study of Optimization Commits in Open Source Unity Projects

开发者如何优化虚拟现实应用:开源 Unity 项目中优化提交的研究
ICSE 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE)2021匹配度 1/10 · 论文是VR/Unity性能优化的软件工程实证研究,仅在生命周期阶段分析中把静态分析当工具使用,不涉及PL→AI、AI→PL、浮点程序分析、贝叶斯程序分析或LLM/Agent相关核心方向。引用 47 inbox
Fariha Nusrat, Foyzul Hassan, Hao Zhong, Xiaoyin Wang
crossref: 2026-09-12dblp: 2026-09-12

AI 速览

一句话:首个对45个开源Unity VR项目中183次性能优化的实证研究,分类优化并分析其生命周期影响与效果。

虚拟现实应用需双眼实时渲染,计算开销高且可穿戴设备资源受限,性能优化至关重要,但其优化实践与传统软件可能不同。本文首次对45个开源 Unity VR 软件项目中的183次真实性能优化进行实证研究。作者人工将优化划分为11类,并结合静态分析识别其影响的 VR 应用生命周期阶段,分析优化的复杂度、设计与行为效应,以及大型组织项目与个人项目之间的差异。结果发现,图形简化(24.0%)、渲染优化(16.9%)、语言/API优化(15.3%)、堆内存规避(14.8%)和值缓存(12.0%)最常见;游戏逻辑更新(30.4%)与场景初始化前(20.0%)是最常受影响阶段;45.9%的优化带来行为或设计影响,39.3%为系统性修改;组织项目与个人项目的优化类别分布差异显著。

问题
VR 应用因双眼实时渲染和可穿戴设备资源受限而面临性能瓶颈,但其真实优化实践与传统软件有何不同尚缺乏实证理解。
方法
收集 45 个开源 Unity VR 项目的 183 次性能优化提交,人工归为 11 类,并用静态分析关联 VR 应用生命周期阶段,分析复杂度、设计/行为效应及组织与个人项目差异。
评估
通过人工分类、静态分析和跨项目统计,报告常见优化类别、受影响生命周期阶段、行为/设计效应比例以及组织/个人项目间的分布差异。
原文摘要(Abstract)

Virtual Reality (VR) is an emerging technique that provides immersive experience for users. Due to the high computation cost of rendering real-time animation twice (for both eyes) and the resource limitation of wearable devices, VR applications often face performance bottlenecks and performanceoptimization plays an important role in VR software develop-ment. Performance optimizations of VR applications can be very different from those in traditional software as VR involves more elements such as graphics rendering and real-time animation. In this paper, we present the first empirical study on 183 real-world performance optimizations from 45 VR software projects. In particular, we manually categorized the optimizations in to 11 categories, and applied static analysis to identify how they affect different life-cycle phases of VR applications. Furthermore, we studied the complexity and design / behavior effects of performance optimizations, and how optimizations are different between large organizational software projects and smaller personal software projects. Our major findings include: (1) graphics simplification (24.0%), rendering optimization (16.9%), language / API optimization (15.3%), heap avoidance (14.8%), and valuecaching (12.0%) are the most common categories of performance optimization in VR applications; (2) game logic updates (30.4%) and before-scene initialization (20.0%) are the most common life-cycle phases affected by performance issues; (3) 45.9% of the optimizations have behavior and design effects and 39.3% of the optimizations are systematic changes; (4) the distributionsof optimization classes are very different between organizational VR projects and personal VR projects.

链接与引用

DOI 原文 · DBLP

BibTeX
@inproceedings{NusratHZW21,
  title = {How Developers Optimize Virtual Reality Applications: A Study of Optimization Commits in Open Source Unity Projects},
  author = {Fariha Nusrat and Foyzul Hassan and Hao Zhong and Xiaoyin Wang},
  booktitle = {ICSE},
  year = {2021},
  doi = {10.1109/icse43902.2021.00052}
}