Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors introduce ReLIQS, a new model for judging image quality without needing reference images. Their approach can handle images of any size without losing important details, and it learns from many different quality studies at once. ReLIQS uses a smart method to pick the most important parts of an image to analyze, making it efficient and accurate. Tests show it works better than previous methods across various types of images and distortions while using similar or less computing power.
No-reference image quality assessmentResolution-agnosticCLIP modelMultiscale patchesPerceptual Importance EstimatorLatent Quality AxisImage distortionSubjective quality studiesComputational efficiencyImage quality metrics
Authors
Hakan Emre Gedik, Shashank Gupta, Alan Bovik
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.