Metraipolis › archive › dc_eef640057cd8
From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment — arXiv:2609.07346
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07346
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:11:46.741Z
- SHA-256 of the archived text
8285340bf38954095c216d368ab720985315b97ba616f32c109af48aa554347a- Stable URL of this page
https://metraipolis.com/documento/dc_eef640057cd8
How to cite
From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment — arXiv:2609.07346 — arXiv (en), https://arxiv.org/abs/2609.07346 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eef640057cd8 (Metraipolis archive dc_eef640057cd8, sha256 8285340bf38954095c216d368ab720985315b97ba616f32c109af48aa554347a)
BibTeX
@misc{dceef640057cd8,
title = {From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment — arXiv:2609.07346},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07346},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eef640057cd8; sha256 8285340bf38954095c216d368ab720985315b97ba616f32c109af48aa554347a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07346. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.07346 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T14:49:57.210Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).