Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency

• URL: http://arxiv.org/abs/2608.01730v1
• Date: Mon, 03 Aug 2026 05:54:06 GMT
• Title: Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency
• Abstract summary: No-reference image quality assessment (NR IQA) has recently benefited from deep and multimodal models.<n>We present textbfReLIQS, a model for textbfResolution-agnostic textbfLearning for textbfImage textbfQuality with textbfSaliency.<n>ReLIQS is a CLIP-based multiscale patch-driven architecture that learns both emphwhere to look and emphhow to judge quality
• Score: 1.6806593639401994
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: No-reference image quality assessment (NR IQA) has recently benefited from deep and multimodal models, yet many SOTA systems still violate at least one basic requirement: they either discard critical quality cues via aggressive resizing, fail to generalize across resolutions, cannot be jointly trained on heterogeneous IQA datasets with mismatched MOS scales, or require prohibitive computation. We present \textbf{ReLIQS}, a model for \textbf{Re}solution-agnostic \textbf{L}earning for \textbf{I}mage \textbf{Q}uality with \textbf{S}aliency, which is resolution-agnostic, preserves original-resolution quality cues, learns from multiple subjective studies, and remains computationally efficient and budget-adaptive. ReLIQS is a CLIP-based multiscale patch-driven architecture that learns both \emph{where to look} and \emph{how to judge} quality. Fixed-size patches are sampled across multiple resolutions, including the original resolution, and encoded with a CLIP vision backbone. A lightweight Perceptual Importance Estimator then predicts IQA-specific importance maps to select a small set of informative patches, and a Latent Quality Axis Module aggregates their embeddings into a single image-level score. Across authentic, synthetic, and AIGC benchmarks spanning diverse resolutions and distortions, ReLIQS generalizes better than strong CNN-, CLIP-, and MLLM-based baselines with matching or reduced computational cost.

Related papers

• Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints [1.0885910878567457]
  Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded query (probe) images against low-quality (LQ) enrollment imagery.<n>We propose a unified framework that combines three main components: (1) Local Probability Margin (LPM), which estimates per-sample difficulty directly from the model's discriminative landscape; (2) Nested Attention Module (NAM), a new low-rank adapter module that embeds a self-attention mechanism within selected transformer layers; and (3) Quality Gating Protocol (QGP), where an off-the-shelf image quality estimator modulates the adapter contribution
  arXiv  Detail & Related papers  (2026-09-01T10:04:12Z)
• Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing [10.754977682331855]
  "Thinking with Images" paradigms induce spurious "cropping-implies-degradation" biases and misinterprets natural depth-of-field as artifacts.<n>We propose Q-Probe, the first agentic IQA framework designed to scale IQA to high resolution via context-aware probing.<n>Q-Probe achieves state-of-the-art performance in high-resolution settings while maintaining superior efficacy across resolution scales.
  arXiv  Detail & Related papers  (2026-01-21T08:02:32Z)
• 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)
• Structural Similarity in Deep Features: Image Quality Assessment Robust to Geometrically Disparate Reference [22.323905448096284]
  We propose a unified, non-training-based Deep Structural Similarity (DeepSSIM) approach to address the above problems.<n>The proposed method achieves state-of-the-art performance on AR-IQA datasets and shows strong robustness to various GDR-IQA test cases.
  arXiv  Detail & Related papers  (2024-12-27T09:51:23Z)
• Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models [93.91086467402323]
  Gradient-Regulated Meta-Prompt IQA Framework (GRMP-IQA) designed to efficiently adapt the visual-language pre-trained model, CLIP, to IQA tasks.<n> GRMP-IQA consists of two core modules: (i) Meta-Prompt Pre-training Module and (ii) Quality-Aware Gradient Regularization.
  arXiv  Detail & Related papers  (2024-09-09T07:26:21Z)
• 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)
• Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment [8.431867616409958]
  No-Reference Image Quality Assessment (NR-IQA) focuses on designing methods to measure image quality in alignment with human perception when a high-quality reference image is unavailable.<n>Most state-of-the-art NR-IQA approaches are opinion-aware, i.e. they require human annotations for training.<n>We propose QualiCLIP, a CLIP-based self-supervised opinion-unaware approach that does not require human opinions.
  arXiv  Detail & Related papers  (2024-03-17T11:32:18Z)
• Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment [49.36799270585947]
  No-reference point cloud quality assessment (NR-PCQA) aims to automatically evaluate the perceptual quality of distorted point clouds without available reference. We propose a novel contrastive pre-training framework tailored for PCQA (CoPA) Our method outperforms the state-of-the-art PCQA methods on popular benchmarks.
  arXiv  Detail & Related papers  (2024-03-15T07:16:07Z)
• Learning Generalizable Perceptual Representations for Data-Efficient No-Reference Image Quality Assessment [7.291687946822539]
  A major drawback of state-of-the-art NR-IQA techniques is their reliance on a large number of human annotations. We enable the learning of low-level quality features to distortion types by introducing a novel quality-aware contrastive loss. We design zero-shot quality predictions from both pathways in a completely blind setting.
  arXiv  Detail & Related papers  (2023-12-08T05:24:21Z)
• KonX: Cross-Resolution Image Quality Assessment [6.658103076536836]
  We present the first study of its kind that disentangles and examines the two issues separately via KonX. We show that objective IQA methods have a scale bias, which reduces their predictive performance. We propose a multi-scale and multi-column architecture that improves performance over previous state-of-the-art IQA models.
  arXiv  Detail & Related papers  (2022-12-12T10:23:48Z)
• Image Quality Assessment using Contrastive Learning [50.265638572116984]
  We train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem. We show through extensive experiments that CONTRIQUE achieves competitive performance when compared to state-of-the-art NR image quality models. Our results suggest that powerful quality representations with perceptual relevance can be obtained without requiring large labeled subjective image quality datasets.
  arXiv  Detail & Related papers  (2021-10-25T21:01:00Z)

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.