Metraipolis › archive › dc_9ffaebca5782

MCIQA-2K: A Multi-Dimensional Dataset and No-Reference Quality Assessment Benchmark for Colorized Images — arXiv:2609.14495

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.14495
License (as archived): CC0-1.0
Archived: 2026-10-16T01:53:11.687Z
SHA-256 of the archived text: 01289ca15d852dc47f5d820d2220fdb6d31e644ab1c759851fef2178909deae3
Stable URL of this page: https://metraipolis.com/documento/dc_9ffaebca5782

How to cite

MCIQA-2K: A Multi-Dimensional Dataset and No-Reference Quality Assessment Benchmark for Colorized Images — arXiv:2609.14495 — arXiv (en), https://arxiv.org/abs/2609.14495 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ffaebca5782 (Metraipolis archive dc_9ffaebca5782, sha256 01289ca15d852dc47f5d820d2220fdb6d31e644ab1c759851fef2178909deae3)

BibTeX

@misc{dc9ffaebca5782,
  title = {MCIQA-2K: A Multi-Dimensional Dataset and No-Reference Quality Assessment Benchmark for Colorized Images — arXiv:2609.14495},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14495},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ffaebca5782; sha256 01289ca15d852dc47f5d820d2220fdb6d31e644ab1c759851fef2178909deae3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14495. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image colorization is an inherently ill-posed task, since a single grayscale image may correspond to multiple plausible colorized results. Consequently, conventional full-reference image quality assessment (IQA) metrics fail to accurately reflect human perceptual preferences for colorized images. In this paper, we present MCIQA-2K, a large-scale multi-dimensional benchmark specifically designed for no-reference quality assessment of colorized images. We construct a dataset containing 2,000 colorized images generated by five representative colorization models, together with human annotations across three perceptual dimensions: color smearing, semantic color misalignment, and global naturalness. Building upon the proposed benchmark, we further introduce MCIQA, a dedicated multi-branch NR-IQA framework for colorized images. Extensive experiments demonstrate that MCIQA significantly outperforms existing full-reference and no-reference IQA methods on the proposed benchmark, while also exhibiting competitive generalization capability on several widely-used IQA datasets. The dataset and code are publicly available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.14495 — 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 2026-10-16T01:25:23.591Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).