Metraipolis › archive › dc_a7b05bdb708d

LLaVA-Assessor: Building the Foundation LMM For Visual Quality Assessment — arXiv:2609.26205

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26205
License (as archived)
CC0-1.0
Archived
2026-10-08T16:39:35.761Z
SHA-256 of the archived text
7cceac7a8672330a4a8fe20e397f48fa0615c1841820e740dd39f0558508a726
Stable URL of this page
https://metraipolis.com/documento/dc_a7b05bdb708d

How to cite

LLaVA-Assessor: Building the Foundation LMM For Visual Quality Assessment — arXiv:2609.26205 — arXiv (en), https://arxiv.org/abs/2609.26205 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a7b05bdb708d (Metraipolis archive dc_a7b05bdb708d, sha256 7cceac7a8672330a4a8fe20e397f48fa0615c1841820e740dd39f0558508a726)
BibTeX
@misc{dca7b05bdb708d,
  title = {LLaVA-Assessor: Building the Foundation LMM For Visual Quality Assessment — arXiv:2609.26205},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26205},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a7b05bdb708d; sha256 7cceac7a8672330a4a8fe20e397f48fa0615c1841820e740dd39f0558508a726},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26205. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Aligning with the human visual system~(HVS) in perceiving and evaluating the quality of visual signals is a central objective of machine-vision-based visual quality assessment systems. With the rapid progress of large multi-modal models~(LMMs), visual question answering provides a promising paradigm for building unified foundation models for visual quality assessment under multi-modal and multi-task scenarios. Inspired by the classical ``perception-decision" process in HVS-based quality evaluation, we formulate visual quality assessment for LMM-based machine vision as two complementary tasks: ``quality interpretation'' and ``quality scoring". Centered on these objectives, we propose LLaVA-Assessor, a unified data construction and model training system. To support multi-modal inputs, we design an adaptive model architecture that enables efficient processing of both images and videos. For data construction, we develop rigorous human annotation protocols and a novel machine-synthesis-dominated data expansion pipeline to build a large-scale and high-quality datasets. Furthermore, we introduce a simple yet effective prompt disentanglement strategy to alleviate training-objective confusion in multi-task learning, thereby enabling stable and coherent joint training. The resulting all-in-one LMM LLaVA-Assessor-GIGA achieves superior performance on $11$ image/video quality scoring test sets and 4 visual quality interpretation benchmarks. Extensive results demonstrate the effectiveness of integrating structured data construction, adaptive model design, and multi-task joint training for automated visual quality assessment. Our work provides compelling insights for developing foundation LMMs for automatic visual quality assessment. Project page at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.26205 — 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 2026-10-08T15:56:18.188Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).