Metraipolis › archive › dc_2bf5ae5df43c

MR-IQA-2: Faithful Image Quality Reflection via Fine-Grained Credit Assignment — arXiv:2608.18579

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18579
License (as archived)
CC0-1.0
Archived
2026-10-18T13:45:12.783Z
SHA-256 of the archived text
4f1c28c15966e3db9ee1a38b65bba69282bab6f77c1347e1de79a2c88143c925
Stable URL of this page
https://metraipolis.com/documento/dc_2bf5ae5df43c

How to cite

MR-IQA-2: Faithful Image Quality Reflection via Fine-Grained Credit Assignment — arXiv:2608.18579 — arXiv (en), https://arxiv.org/abs/2608.18579 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bf5ae5df43c (Metraipolis archive dc_2bf5ae5df43c, sha256 4f1c28c15966e3db9ee1a38b65bba69282bab6f77c1347e1de79a2c88143c925)
BibTeX
@misc{dc2bf5ae5df43c,
  title = {MR-IQA-2: Faithful Image Quality Reflection via Fine-Grained Credit Assignment — arXiv:2608.18579},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18579},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bf5ae5df43c; sha256 4f1c28c15966e3db9ee1a38b65bba69282bab6f77c1347e1de79a2c88143c925},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18579. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal large language models (MLLMs) have shown strong potential for image quality assessment (IQA) by improving consistency between quality ratings and their underlying reasoning. However, most approaches supervise reasoning through human-provided ratings and rarely examine whether it faithfully reflects image quality. Rating accuracy alone does not ensure faithful reasoning; a shared reward also obscures supervision sources and may reinforce unfaithful reasoning when a correct rating occurs by chance. To improve the faithfulness and reliability of blind IQA, we aim to (1) decouple credit assignment for reasoning and rating and (2) provide verifiable supervision for faithful reasoning. We introduce MR-IQA-2, an actor-editor-judge framework that operationalizes reasoning-editing-reflection. The actor generates quality reasoning for an input image, and the editor revises the image according to the identified quality factors. A frozen judge compares the original and edited images and provides reflective supervision for the actor's reasoning. MR-IQA-2 further uses fine-grained credit assignment to decouple reasoning and rating supervision. Judge feedback supervises reasoning, whereas human ratings supervise the predicted rating. Masked token-specific updates distinguish these signals while preserving the causal relation from reasoning to rating. Across IQA benchmarks, MR-IQA-2 achieves competitive rating alignment with humans. Visual reflection also enables richer and more faithful visual understanding beyond rating, which may inform image-quality optimization and related downstream tasks. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.18579 — 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 2026-10-18T13:41:17.957Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).