发表机构
College of Applied Technology Shenzhen University; College of Electronics and Information Engineering Shenzhen University（深圳大学应用技术学院; 深圳大学电子与信息工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文综述三维高斯泼溅质量评估，分析失真特性、主观基准与客观指标可靠性，指出协议依赖性问题，并总结开放挑战与构建可比评估的实用指南。
AI 中文摘要
三维高斯泼溅（3DGS）已成为实时新视角渲染、压缩和沉浸式内容交付的实用场景表示方法。然而，其质量评估在很大程度上仍遵循渲染视图代理协议，即采样相机姿态、渲染图像或视频，并应用继承的图像和视频质量指标。尽管这种方法便捷，但它并未完全捕捉源自高斯原语分布、泼溅与可见性行为以及轨迹相关伪影的3DGS原生退化。本综述从四个角度回顾了近期3DGS质量评估研究，涵盖失真特性、主观基准、客观指标可靠性以及原生3DGS评估的新兴方向。纵观文献，我们发现不同基准构建了不同的质量概念，且指标有效性高度依赖协议，随失真源、刺激格式以及视图和轨迹采样而变化。最后，我们总结了开放挑战，并概述了构建更具可比性和代表性的3DGS-QA评估的实用指南。
英文摘要
3D Gaussian Splatting (3DGS) has become a practical scene representation for real-time novel-view rendering, compression, and immersive content delivery. However, its quality assessment still largely follows rendered-view proxy protocols that sample camera poses, render images or videos, and apply inherited image and video quality metrics. While convenient, this practice does not fully capture 3DGS-native degradations that originate from Gaussian primitive distributions, splatting and visibility behavior, and trajectory-dependent artifacts. This survey reviews recent 3DGS quality assessment studies from four perspectives, covering distortion characteristics, subjective benchmarks, objective metric reliability, and emerging directions for native 3DGS evaluation. Across the literature, we find that different benchmarks construct different notions of quality, and that metric effectiveness is highly protocol dependent, varying with distortion sources, stimulus formats, and view and trajectory sampling. Finally, we summarize open challenges and outline practical guidelines for building more comparable and representative 3DGS-QA evaluations.
CommentsPublished in: 2026 11th International Conference on Image, Vision and Computing (ICIVC)
DOI：10.1109/ICIVC70586.2026.11686689
