vix.ing · top · new · best · stats

MUSIQ: Multi-scale Image Quality Transformer

2021/08/12 by Junjie Ke, Qifei Wang, Ke, Junjie +7 · 301 citations
Computer Science · Engineering · #Advanced Image Fusion Techniques #Artificial intelligence #Computer science #Computer vision #Convolutional neural network #Data mining #Embedding #Engineering #Image (mathematics) #Image Enhancement Techniques #Image and Video Quality Assessment #Image quality #Pattern recognition (psychology) #Representation (politics) #Scale (ratio) #Transformer #cs.CV

paper · pdf · doi:10.48550/arxiv.2108.05997

published in arXiv (Cornell University) (Cornell University) · ICCV 2021

arxiv created 2021/08/12 · openalex publication_date 2021/08/12 · arxiv updated 2021/08/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Image quality assessment (IQA) is an important research topic for understanding and improving visual experience. The current state-of-the-art IQA methods are based on convolutional neural networks (CNNs). The performance of CNN-based models is often compromised by the fixed shape constraint in batch training. To accommodate this, the input images are usually resized and cropped to a fixed shape, causing image quality degradation. To address this, we design a multi-scale image quality Transformer (MUSIQ) to process native resolution images with varying sizes and aspect ratios. With a multi-scale image representation, our proposed method can capture image quality at different granularities. Furthermore, a novel hash-based 2D spatial embedding and a scale embedding is proposed to support the positional embedding in the multi-scale representation. Experimental results verify that our method can achieve state-of-the-art performance on multiple large scale IQA datasets such as PaQ-2-PiQ, SPAQ and KonIQ-10k.

Citations

Cited by

Related