Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network

By Shaolin Su, Qingsen Yan, Cheng Zhang, Xin Ge, Jinqiu Sun, Yanning Zhang. Computer Vision and Pattern Recognition, 2020

927 citations recorded by the source corpus.

Blind image quality assessment (BIQA) for authentically distorted images has always been a challenging problem, since images captured in the wild include varies contents and diverse types of distortions. The vast majority of prior BIQA methods focus on how to predict synthetic image quality, but fail when applied to real-world distorted images. To deal with the challenge, we propose a self-adaptive hyper network architecture to blind assess image quality in the wild. We separate the IQA procedure into three stages including content understanding, perception rule learning and quality predicting. After extracting image semantics, perception rule is established adaptively by a hyper network, and then adopted by a quality prediction network. In our model, image quality can be estimated in a self-adaptive manner, thus generalizes well on diverse images captured in the wild. Experimental results verify that our approach not only outperforms the state-of-the-art methods on challenging authentic image databases but also achieves competing performances on synthetic image databases, though it is not explicitly designed for the synthetic task.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/b45593aa1a0f1363f33326e8bfd9c8e4d5ed86bd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment (2022, methodology): “Hyper-IQA [37] separated the features into the low-level and high-level features and transformed the latter to redirect the former.”
No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency (2021, background): “[42] proposed a model that extracts content features from the deep model in different scales and pools them to predict image quality.”
Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels (2023, methodology): “To address this need, from handcraft approaches (Mit-tal et al., 2013; 2012) to deep-neural-network-based meth-ods (Talebi & Milanfar, 2018; Zhang et al., 2020; Ke et al., 2021), the endeavor to improve the accuracies of visual assessors never stops.”
Exploring CLIP for Assessing the Look and Feel of Images (2022, methodology): “These results are comparable with state-of-the-art deep learning based methods [15,22,36,51], showing the potential of large-scale language-vision training.”
Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective (2023, methodology): “Being separately trained on each individual dataset with a separate group of parameters, DBCNN [76], HyperIQA [55], and TreS [13] achieve promising performance on all six datasets.”
MUSIQ: Multi-scale Image Quality Transformer (2021, methodology): “In the past years, researchers proposed many IQA methods: early natural scene statistics based [13, 25, 27, 45], codebook-based [38, 40] and CNN-based [11, 33, 34, 41, 47].”