MAMIQA: No-Reference Image Quality Assessment Based on Multiscale Attention Mechanism With Natural Scene Statistics
No-Reference Image Quality Assessment aims to evaluate the perceptual quality of an image, according to human perception. Many recent studies use Transformers to assign different self-attention mechanisms to distinguish regions of an image, simulating the perception of the human visual system (HVS). However, the quadratic computational complexity caused by the self-attention mechanism is time-consuming and expensive. Meanwhile, the image resizing in the feature extraction stage loses the full-size image quality. To address these issues, we propose a lightweight attention mechanism using decomposed large-kernel convolutions to extract multiscale features, and a novel feature enhancement module to simulate HVS. We also propose to compensate the information loss caused by image resizing, with supplementary features from natural scene statistics. Experimental results on five standard datasets show that the proposed method surpasses the SOTA, while significantly reducing the computational costs.
Code (1)
Tasks
Image Quality AssessmentNo-Reference Image Quality AssessmentSimilar Papers 제목 키워드 기반
Non-Reference Quality Monitoring of Digital Images using Gradient Statistics and Feedforward Neural Networks
Digital images contain a lot of redundancies, therefore, compressions are applied to reduce the image size without the loss of reasonable image quality. The same become more prominent in the case of videos that contains …
Image Quality AssessmentMS-SCANet: A Multiscale Transformer-Based Architecture with Dual Attention for No-Reference Image Quality Assessment
We present the Multi-Scale Spatial Channel Attention Network (MS-SCANet), a transformer-based architecture designed for no-reference image quality assessment (IQA). MS-SCANet features a dual-branch structure that process…
No-Reference Image Quality AssessmentImage Quality Assessment: Enhancing Perceptual Exploration and Interpretation with Collaborative Feature Refinement and Hausdorff distance
Current full-reference image quality assessment (FR-IQA) methods often fuse features from reference and distorted images, overlooking that color and luminance distortions occur mainly at low frequencies, whereas edge and…
Full reference image quality assessmentFull-Reference Image Quality AssessmentImage Quality AssessmentA survey on IQA
Image quality assessment(IQA) is of increasing importance for image-based applications. Its purpose is to establish a model that can replace humans for accurately evaluating image quality. According to whether the refere…
Deep LearningFull reference image quality assessmentFull-Reference Image Quality AssessmentImage Quality Assessment+2Multiscale structural similarity for image quality assessment
The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural simil…
Full reference image quality assessmentImage GenerationImage Quality AssessmentVideo Quality Assessment