No-Reference Image Quality Assessment: Exploring Intrinsic Distortion Characteristics via Generative Noise Estimation with Mamba

doi:10.1109/TCSVT.2025.3586106

科研成果详情

题名	No-Reference Image Quality Assessment: Exploring Intrinsic Distortion Characteristics via Generative Noise Estimation with Mamba
作者	Lan，Xuting 1; Xian，Weizhi 2,3; Zhou，Mingliang 1; Yan，Jielu 1; Wei，Xuekai 1; Luo，Jun 4; Jia，Weijia 5; Kwong，Sam 6
发表日期	2025
发表期刊	IEEE Transactions on Circuits and Systems for Video Technology
ISSN/eISSN	1051-8215
摘要	In the field of no-reference image quality assessment (NR-IQA), the visual masking effect has long been a challenging issue. Although existing methods attempt to alleviate the interference caused by masking by generating pseudoreference images, the quality of these images is often constrained by the accuracy and reconstruction capabilities of image restoration algorithms. This can introduce additional biases, thereby affecting the reliability of the evaluation results. To address this problem, we propose a novel generative “noise” estimation framework (GNE-Vim) that eliminates the need for pseudoreference images. Instead, it deeply decouples the distortion components from degraded images and performs quality-aware modelling of these components. During the training phase, the model leverages both reference images and distortion components to guide the learning of the true distortion distribution. In the inference phase, quality prediction is conducted directly on the basis of the decoupled distortion components, making the evaluation results more aligned with human subjective perception. The experimental results demonstrate that the proposed method achieves strong performance across datasets containing various types of distortions.
关键词	fusion network generative noise estimation No-reference image quality assessment vision mamba
DOI	10.1109/TCSVT.2025.3586106
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-105010295098
引用统计
文献类型	期刊论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/13723
专题	北师香港浸会大学
通讯作者	Xian，Weizhi; Zhou，Mingliang
作者单位	1.Chongqing University,School of Computer Science,Chongqing,400044,China 2.Chongqing University,College of Computer Science,Chongqing,400044,China 3.Harbin Institute of Technology,Chongqing Research Institute of Harbin Institute of Technology,Chongqing,401151,China 4.Chongqing University,School of Mechanical and Vehicle Engineering,Chongqing,400044,China 5.BNU-UIC Institute of Artificial Intelligence and Future Networks,Beijing Normal University,Zhuhai and Guangdong Key Lab of AI Multi-Modal Data Processing,BNU-HKBU United International College,Zhuhai,519087,China 6.Lingnan University,Department of Computing and Decision Science,Hong Kong
推荐引用方式 GB/T 7714	Lan，Xuting,Xian，Weizhi,Zhou，Minglianget al. No-Reference Image Quality Assessment: Exploring Intrinsic Distortion Characteristics via Generative Noise Estimation with Mamba[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2025.
APA	Lan，Xuting., Xian，Weizhi., Zhou，Mingliang., Yan，Jielu., Wei，Xuekai., .. & Kwong，Sam. (2025). No-Reference Image Quality Assessment: Exploring Intrinsic Distortion Characteristics via Generative Noise Estimation with Mamba. IEEE Transactions on Circuits and Systems for Video Technology.
MLA	Lan，Xuting,et al."No-Reference Image Quality Assessment: Exploring Intrinsic Distortion Characteristics via Generative Noise Estimation with Mamba". IEEE Transactions on Circuits and Systems for Video Technology (2025).