From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment

• URL: http://arxiv.org/abs/2609.08316v1
• Date: Tue, 08 Sep 2026 06:39:25 GMT
• Title: From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment
• Abstract summary: We propose GS-IQA, a framework that reformulates IQA as a progressive Where--What--How diagnosis.<n>It emulates the human perceptual process from an initial glance to closer scrutiny.<n>It consistently surpasses state-of-the-art methods in distortion localization, recognition, and severity estimation.
• Score: 20.450708458726627
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-modal large language models (MLLMs) have demonstrated significant potential in image quality assessment (IQA) by bridging visual perception with descriptive evaluations. However, existing approaches mainly focus on holistic quality prediction, often functioning as black boxes that provide limited insight into where distortions occur and how they affect perceived quality, hindering fine-grained analysis of localized and heterogeneous degradations. We propose GS-IQA, a framework that reformulates IQA as a progressive Where--What--How diagnosis, emulating the human perceptual process from an initial glance to closer scrutiny. Since a severity judgment is meaningful only for a correctly localized and recognized region, we realize this progression through a two-stage reinforcement learning paradigm that respects such dependencies: the glance stage uses a perception-gated reward to establish where degradations lie and what they are, activating severity feedback only once both are correct, while the scrutiny stage introduces online reward-conditioned degradation generation to synthesize hard examples targeted at the model's perceptual bottlenecks, sharpening its discrimination of subtle severity variations. To enable systematic evaluation, we construct Diag-Bench, a region-level IQA benchmark of about 25K curated samples spanning 12 distortion types and five ordinal severity levels. Extensive experiments show that GS-IQA consistently surpasses state-of-the-art methods in distortion localization, recognition, and severity estimation, and that its diagnostic representations transfer effectively to conventional global quality prediction across diverse external benchmarks. Code and data will be released.

Related papers

• EFIQA: Explainable Fundus Image Quality Assessment via Anatomical Priors [3.868953398237752]
  We propose EFIQA, a framework that requires no quality-related supervision and produces spatial quality maps by design.<n>For fundus photography, we instantiate this as a two-stage approach, by first training an unsupervised anomaly detector via masked anatomical inpainting to identify regions of missing vasculature.
  arXiv  Detail & Related papers  (2026-06-18T11:31:08Z)
• ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling [62.983372215479925]
  Streaming and generative systems require incremental estimation from partial audio.<n>We propose ANCHOR, reformulating incremental assessment as a multi-resolution autore task.<n> Experiments show substantial robustness under partial input, including a 48% PLCMOS error reduction on 2-second prefixes.
  arXiv  Detail & Related papers  (2026-06-08T22:46:30Z)
• The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation [18.83395586542378]
  Multimodal Large Language Models (MLLMs) are increasingly integrated with Retrieval-Augmented Generation (RAG)<n>We identify and formalize the phenomenon of recorruption, where the introduction of even perfectly accurate "oracle" context causes a capable model to abandon an initially correct prediction.<n>We propose Bottleneck Attention Intervention for Recovery (BAIR), a parameter-free, inference-time framework that restores visual saliency and applies position-aware penalties to textual distractors.
  arXiv  Detail & Related papers  (2026-05-07T02:27:04Z)
• Development and evaluation of CADe systems in low-prevalence setting: The RARE25 challenge for early detection of Barrett's neoplasia [8.843983707422955]
  Computer-aided detection of early neoplasia in Barrett's esophagus is a low-prevalence surveillance problem.<n>The RARE25 challenge addresses this gap by introducing a large-scale, prevalence-aware benchmark for neoplasia detection.<n>Eleven teams from seven countries submitted approaches using diverse architectures, pretraining, ensembling, and calibration strategies.
  arXiv  Detail & Related papers  (2026-04-13T08:30:35Z)
• Radiology Report Generation for Low-Quality X-Ray Images [47.455316078409]
  Vision-Language Models (VLMs) have significantly advanced automated Radiology Report Generation (RRG)<n>Existing methods implicitly assume high-quality inputs, overlooking the noise and artifacts prevalent in real-world clinical environments.<n>We propose a robust report generation framework explicitly designed for image quality variations.
  arXiv  Detail & Related papers  (2026-04-11T12:42:37Z)
• DR.Experts: Differential Refinement of Distortion-Aware Experts for Blind Image Quality Assessment [9.682871853344226]
  We introduce DR.Experts, a novel prior-driven BIQA framework designed to explicitly incorporate distortion priors.<n> DR.Experts begins by leveraging a degradation-aware vision-language model to obtain distortion-specific priors.<n>The refined priors, along with semantics and bridging representation, are then fused by a proposed mixture-of-experts style module.<n>This mechanism weights each distortion-specific feature as per its perceptual impact, ensuring that the final quality prediction aligns with human perception.
  arXiv  Detail & Related papers  (2026-02-10T08:41:40Z)
• Fine-Grained Human Pose Editing Assessment via Layer-Selective MLLMs [70.31435391393642]
  We introduce a benchmark comprising 1,700 standardized samples from 17 state-of-the-art editing models.<n>We propose a unified framework based on layer-selective multimodal large language models (MLLMs)<n>Our framework achieves superior performance in both authenticity detection and multi-dimensional quality regression.
  arXiv  Detail & Related papers  (2026-01-15T13:22:07Z)
• Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization [53.82400605816587]
  Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation.<n>A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios.<n>We introduce Continual AQA (CAQA), which equips with Continual Learning capabilities to handle evolving distributions.
  arXiv  Detail & Related papers  (2025-10-08T10:09:47Z)
• HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessment [10.761579471650771]
  HiRQA is a self-supervised, opinion-unaware framework that offers a hierarchical, quality-aware embedding through a combination of ranking and contrastive learning.<n>For real-time deployment, we introduce textbfHiRQA-S, a lightweight variant with an inference time of only 3.5 ms per image.
  arXiv  Detail & Related papers  (2025-08-20T23:48:21Z)
• 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)
• Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild [98.48284827503409]
  We develop a textitunified BIQA model and an approach of training it for both synthetic and realistic distortions. We employ the fidelity loss to optimize a deep neural network for BIQA over a large number of such image pairs. Experiments on six IQA databases show the promise of the learned method in blindly assessing image quality in the laboratory and wild.
  arXiv  Detail & Related papers  (2020-05-28T13:35:23Z)

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.