Multi-Granularity Reasoning for Image Quality Assessment via Attribute-Aware Reinforcement Learning to Rank

• URL: http://arxiv.org/abs/2604.09704v1
• Date: Tue, 07 Apr 2026 16:07:55 GMT
• Title: Multi-Granularity Reasoning for Image Quality Assessment via Attribute-Aware Reinforcement Learning to Rank
• Abstract summary: We propose MG-IQA (Multi-Granularity IQA), a multi-granularity reasoning framework that extends RL2R to jointly assess overall image quality and fine-grained quality attributes.<n>Our approach introduces three key innovations: (1) an attribute-aware prompting strategy that elicits structured multi-attribute reasoning from VLMs; (2) a multi-dimensional Thurstone reward model that computes attribute-specific fidelity rewards for group relative policy optimization; and (3) a cross-domain alignment mechanism that enables stable joint training across synthetic distortion, authentic distortion, and AI-generated image datasets without perceptual scale re-alignment.
• Score: 12.385224959925523
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in reasoning-induced image quality assessment (IQA) have demonstrated the power of reinforcement learning to rank (RL2R) for training vision-language models (VLMs) to assess perceptual quality. However, existing approaches operate at a single granularity, predicting only an overall quality score, while overlooking the multi-dimensional nature of human quality perception, which encompasses attributes such as sharpness, color fidelity, noise level, and compositional aesthetics. In this paper, we propose MG-IQA (Multi-Granularity IQA), a multi-granularity reasoning framework that extends RL2R to jointly assess overall image quality and fine-grained quality attributes within a single inference pass. Our approach introduces three key innovations: (1) an attribute-aware prompting strategy that elicits structured multi-attribute reasoning from VLMs; (2) a multi-dimensional Thurstone reward model that computes attribute-specific fidelity rewards for group relative policy optimization; and (3) a cross-domain alignment mechanism that enables stable joint training across synthetic distortion, authentic distortion, and AI-generated image datasets without perceptual scale re-alignment. Extensive experiments on eight IQA benchmarks demonstrate that MG-IQA consistently outperforms state-of-the-art methods in both overall quality prediction (average SRCC improvement of 2.1\%) and attribute-level assessment, while generating interpretable, human-aligned quality descriptions.

Related papers

• Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration [21.358966811756645]
  Real-world image restoration aims to restore high-quality (HQ) images from degraded low-quality (LQ) inputs captured under uncontrolled conditions.<n>Existing methods typically depend on ground-truth (GT) supervision, assuming that GT provides perfect reference quality.<n>We propose an Image Quality Prior (IQP)-extracted from pre-trained No-Reference Image Quality Assessment (NR-IQA) models-to guide the restoration process toward perceptually optimal outputs explicitly.
  arXiv  Detail & Related papers  (2026-03-31T14:13:10Z)
• Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessment [25.916354359994624]
  We propose Q-Hawkeye, an RL-based reliable visual policy optimization framework.<n>Q-Hawkeye estimates predictive uncertainty using the variance of predicted scores across multiple rollouts.<n>We introduce an Implicit Perception Loss that constrains the model to ground its quality judgments in genuine visual evidence.
  arXiv  Detail & Related papers  (2026-01-30T12:42:32Z)
• Enhancing Image Quality Assessment Ability of LMMs via Retrieval-Augmented Generation [102.10193318526137]
  Large Multimodal Models (LMMs) have recently shown remarkable promise in low-level visual perception tasks.<n>We introduce IQARAG, a training-free framework that enhances LMMs' Image Quality Assessment (IQA) ability.<n>IQARAG leverages Retrieval-Augmented Generation (RAG) to retrieve some semantically similar but quality-variant reference images with corresponding Mean Opinion Scores (MOSs) for input image.
  arXiv  Detail & Related papers  (2026-01-13T08:00:02Z)
• PreResQ-R1: Towards Fine-Grained Rank-and-Score Reinforcement Learning for Visual Quality Assessment via Preference-Response Disentangled Policy Optimization [12.993619998545633]
  PreResQ-R1 is a Preference-Response Disentangled Reinforcement Learning framework.<n>It unifies absolute score regression and relative ranking consistency within a single reasoning-driven optimization scheme.<n>It achieves state-of-the-art results across 10 IQA and 5 VQA benchmarks under both SRCC and PLCC metrics.
  arXiv  Detail & Related papers  (2025-11-07T16:19:50Z)
• VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank [30.316630325648834]
  We introduce VisualQuality-R1, a reasoning-induced no-reference IQA (NR-IQA) model, and we train it with reinforcement learning to rank.<n>We show that VisualQuality-R1 consistently outperforms discriminative deep learning-based NR-IQA models.<n>VisualQuality-R1 is capable of generating contextually rich, human-aligned quality descriptions.
  arXiv  Detail & Related papers  (2025-05-20T14:56:50Z)
• IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond [56.99331967165238]
  Blind Face Restoration (BFR) addresses the challenge of reconstructing degraded low-quality (LQ) facial images into high-quality (HQ) outputs.<n>We propose a novel framework that incorporates an Image Quality Prior (IQP) derived from No-Reference Image Quality Assessment (NR-IQA) models.<n>Our method outperforms state-of-the-art techniques across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-03-12T11:39:51Z)
• Teaching LMMs for Image Quality Scoring and Interpreting [71.1335005098584]
  We propose Q-SiT (Quality Scoring and Interpreting joint Teaching), a unified framework that enables image quality scoring and interpreting simultaneously.<n>Q-SiT is the first model capable of simultaneously performing image quality scoring and interpreting tasks, along with its lightweight variant, Q-SiT-mini.<n> Experimental results demonstrate that Q-SiT achieves strong performance in both tasks with superior generalization IQA abilities.
  arXiv  Detail & Related papers  (2025-03-12T09:39:33Z)
• M3-AGIQA: Multimodal, Multi-Round, Multi-Aspect AI-Generated Image Quality Assessment [65.3860007085689]
  M3-AGIQA is a comprehensive framework that enables more human-aligned, holistic evaluation of AI-generated images.<n>By aligning model outputs more closely with human judgment, M3-AGIQA delivers robust and interpretable quality scores.
  arXiv  Detail & Related papers  (2025-02-21T03:05:45Z)
• Scale Contrastive Learning with Selective Attentions for Blind Image Quality Assessment [15.235786583920062]
  Blind image quality assessment (BIQA) serves as a fundamental task in computer vision, yet it often fails to consistently align with human subjective perception. Recent advances show that multi-scale evaluation strategies are promising due to their ability to replicate the hierarchical structure of human vision. This paper addresses two primary challenges: the significant redundancy of information across different scales, and the confusion caused by combining features from these scales.
  arXiv  Detail & Related papers  (2024-11-13T20:17:30Z)
• Q-Ground: Image Quality Grounding with Large Multi-modality Models [61.72022069880346]
  We introduce Q-Ground, the first framework aimed at tackling fine-scale visual quality grounding. Q-Ground combines large multi-modality models with detailed visual quality analysis. Central to our contribution is the introduction of the QGround-100K dataset.
  arXiv  Detail & Related papers  (2024-07-24T06:42:46Z)
• Multi-Modal Prompt Learning on Blind Image Quality Assessment [65.0676908930946]
  Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. This paper introduces an innovative multi-modal prompt-based methodology for IQA.
  arXiv  Detail & Related papers  (2024-04-23T11:45:32Z)
• Blind Multimodal Quality Assessment: A Brief Survey and A Case Study of Low-light Images [73.27643795557778]
  Blind image quality assessment (BIQA) aims at automatically and accurately forecasting objective scores for visual signals. Recent developments in this field are dominated by unimodal solutions inconsistent with human subjective rating patterns. We present a unique blind multimodal quality assessment (BMQA) of low-light images from subjective evaluation to objective score.
  arXiv  Detail & Related papers  (2023-03-18T09:04:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.