发表机构
Vrije Universiteit Brussel; imec; Electronics and Telecommunications Research Institute (ETRI)（布鲁塞尔自由大学; imec研究院; 电子通信研究院（ETRI））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对辐射场渲染视图质量评估，提出SCODA方法，通过场景流形建模和失真感知判别器，实现无需参考图像的客观评估，在多个基准上验证了与人类判断的高度一致性。
AI 中文摘要
辐射场表示方法（如3D高斯泼溅，3DGS）能够实现高质量的新视角合成，但可能引入来自重建、渲染和压缩的复杂且视角相关的伪影。因此，可靠的感知质量评估（QA）对于评估渲染视图和指导感知保真场景表示的设计至关重要。现有的全参考QA指标需要对齐的参考图像，而近期的跨参考指标通过将测试视图与非对齐参考进行比较来放宽这一要求。然而，在宽基线辐射场设置下，选择可靠的邻近参考可能很困难，尤其是在评估沿任意轨迹和姿态的视图时。我们提出了SCODA，一种轻量级的场景条件客观QA方法，将QA从显式图像到图像的比较转变为场景流形建模。每个场景的高质量观测被表示为深度特征空间中的多元高斯分布，产生一个衡量偏离场景分布的语义保真度分数。一个弱监督的失真感知补丁判别器提供互补的真实感信号，两种线索通过无监督的有界融合策略结合。在多个基准上的实验表明，与人类判断高度一致，并且在GS和NeRF生成的视图和轨迹上具有稳健的泛化能力。代码在此https URL公开可用。
英文摘要
Radiance field representations such as 3D Gaussian Splatting (3DGS) enable high-quality novel view synthesis but can introduce complex, view-dependent artifacts from reconstruction, rendering, and compression. Reliable perceptual quality assessment (QA) is thus essential for evaluating rendered views and guiding the design of perceptually faithful scene representations. Existing full-reference QA metrics require an aligned reference image, while recent cross-reference metrics relax this requirement by comparing a test view with non-aligned references. However, under wide-baseline radiance field settings, selecting a reliable nearby reference can be difficult, particularly when evaluating views along arbitrary trajectories and poses. We propose SCODA, a lightweight scene-conditioned objective QA method that shifts QA from explicit image-to-image comparison to scene-manifold modeling. High-quality observations of each scene are represented as a multivariate Gaussian distribution in deep feature space, producing a semantic fidelity score that measures deviation from the scene distribution. A weakly-supervised distortion-aware patch discriminator provides a complementary realism signal, and both cues are combined through an unsupervised bounded fusion strategy. Experiments on multiple benchmarks show strong agreement with human judgments and robust generalization across GS- and NeRF-generated views and trajectories. Code is publicly available at https://gitlab.com/saeedmp/scoda.
