3DGSI-Assessor：面向3D高斯溅射图像质量评估的大规模数据集与基于大视觉语言模型的方法
3DGSI-Assessor: A Large-Scale Dataset and An LMM-based Method for 3D Gaussian Splatting Image Quality Assessment
浏览论文内容
中文总结 AI 辅助
针对3D高斯溅射压缩的失真评估缺口，提出含15200张图像的多维IQA数据集3DGS-IEval-15K+，并构建基于大视觉语言模型的一体化IQA框架3DGSI-Assessor，该框架在对应数据集上达SOTA且泛化性良好。
中文摘要 AI 辅助
3D高斯溅射（3DGS）已成为实时新视图合成（NVS）的主流表示形式，但其存储占用使得压缩对于实际部署必不可少。3DGS的训练和压缩会引入特定于表示的失真，例如浮伪影和表面散射，而传统图像质量评估（IQA）指标无法捕捉这些失真。此外，几何和颜色属性的独立压缩可能会导致维度特定的解耦失真，必须单独诊断，但现有指标仅报告单一的整体分数。为解决这些缺口，我们提出了3DGS-IEval-15K+，这是一个针对压缩后3DGS的大规模多维IQA数据集，包含来自10个不同场景的15200张图像，由6种代表性3DGS算法在系统设计的压缩级别下生成，并从20个精心选择的视点（涵盖训练视点和具有挑战性的新视点）渲染，标注了45600个均值意见分数（MOS），涉及整体、几何和颜色质量三个维度。基于3DGS-IEval-15K+，我们提出了3DGSI-Assessor，这是一个一体化的3DGS IQA框架，在大视觉语言模型（LMM）中集成了全局语义和维度特定的局部特征，可在单次前向传播中预测所有三个维度。3DGSI-Assessor在3DGS-IEval-15K+上达到了最先进的性能，在其他NVS基准上也表现出具有竞争力的泛化能力。数据集和代码将在该httpsURL发布。
英文摘要
3D Gaussian Splatting (3DGS) has become a dominant representation for real-time novel view synthesis (NVS), yet its storage footprint makes compression indispensable for practical deployment. 3DGS training and compression introduce representation-specific distortions such as floating artifacts and surface scattering, which conventional image quality assessment (IQA) metrics fail to capture. Moreover, the independent compression of geometric and color attributes may lead to decoupled dimension-specific distortions that must be diagnosed separately, yet existing metrics report only a single overall score. To address these gaps, we present 3DGS-IEval-15K+, a large-scale, multi-dimensional IQA dataset for compressed 3DGS, comprising 15,200 images from 10 diverse scenes, produced by 6 representative 3DGS algorithms at systematically designed compression levels and rendered from 20 strategically selected viewpoints spanning both training views and challenging novel views, annotated with 45,600 mean opinion scores (MOSs) across overall, geometry, and color quality. Based on 3DGS-IEval-15K+, we propose 3DGSI-Assessor, an all-in-one 3DGS IQA framework that integrates global semantic and dimension-specific local features within a large multimodal model (LMM), predicting all three dimensions in a single forward pass. 3DGSI-Assessor achieves state-of-the-art performance on 3DGS-IEval-15K+, and exhibits competitive generalization on other NVS benchmarks. Dataset and code will be released at https://github.com/YukeXing/3DGSI-Assessor.
