Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQA

2026-09-15

AI Summary

该研究针对CLIP在NR-IQA中因语义不变性导致的细微感知信号丢失问题，提出了一种跨模态感知对齐适配器（CMPA）和残差增强感知降尺度策略来恢复这些信号。

Abstract

Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contrastive pretraining of CLIP inherently prioritizes semantic invariance, which often suppresses subtle perceptual signals, a phenomenon we term perceptual submergence. Furthermore, standard preprocessing techniques (e.g., cropping and interpolation) further exacerbate the loss of critical high-frequency quality cues. In this paper, we propose the Cross-modal Perception Alignment Adapter (CMPA), a manifold-aware framework designed to disentangle perceptual distortions from dominant semantics. CMPA introduces a Perception-Sensitive Feature Extractor (PFE) that projects CLIP features into a compact, low-dimensional subspace, explicitly magnifying distortion-induced off-manifold deviations. Subsequently, a Cross-Modal Perception Alignment Injector (PAI) aligns these features with quality-aware text anchors and re-injects them into the backbone. To ensure input fidelity, we also devise a Residual-enhanced Perceptual Downscaling strategy that adaptively compensates for resolution-induced information loss using Just Noticeable Difference (JND) guided frequency re-injection. Extensive evaluations on several benchmark datasets demonstrate that our approach significantly outperforms state-of-the-art methods, effectively recovering the perceptual signals submerged in semantic-dense representations.

Problem

• Perceptual Submergence
• No-Reference Image Quality Assessment
• Semantic Invariance
• High-Frequency Quality Cues
• Perceptual Distortions

Innovation

• Cross-modal Perception Alignment Adapter
• Perception-Sensitive Feature Extractor
• Cross-Modal Perception Alignment Injector
• Residual-enhanced Perceptual Downscaling
• Just Noticeable Difference