Fre-QNet: Quaternion Progressive Perception Mechanism with Frequency-Guided Prompt for Blind Image Quality Assessment

Blind Image Quality Assessment (BIQA) faces challenges in enabling computational models to mimic the hierarchical progressive perception mechanisms of the human visual system (HVS). Existing methods often neglect the HVS’s two-stage process—global distortion identification followed by local quality evaluation—and its distinct sensitivity to distortion types. To address this, we propose Fre-QNet, a novel framework integrating two key components: 1) A Quaternion Progressive Perception (QPP) module that hierarchically extracts multi-scale spatial features using quaternion convolution, explicitly simulating the HVS’s global-to-local observation process while enhancing cross-scale interactions; 2) A Frequency Prompting (FP) module that quantifies distortion types and severity in the Fourier domain by leveraging frequency patterns of common distortions and the HVS’s sensitivity variations. The QPP and FP modules collaboratively embed biological vision principles into computational modeling through dual-domain feature learning, with the QPP module directly anchoring the core logic of progressive perception. Experiments on TID2013 and CSIQ benchmarks demonstrate Fre-QNet’s superiority over state-of-the-art methods, validating its effectiveness in matching human perceptual quality judgments. Our source code is available at: https://github.com/hhsda/Fre-QNet .