From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment

2026-09-07

AI Summary

为解决宽基线辐射场设置下的视图质量评估问题，提出SCODA方法，通过场景流形建模而非直接图像比较来衡量语义保真度和真实感。

Abstract

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.

Problem

• Radiance Field
• Quality Assessment
• View Synthesis
• Scene Representation
• Perceptual Fidelity

Innovation

• Scene-conditioned Objective QA
• Scene-manifold Modeling
• Multivariate Gaussian Distribution
• Distortion-aware Patch Discriminator
• Unsupervised Bounded Fusion