MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration
Shunyu Yao, Ming Liu, Zhilu Zhang, Zhaolin Wan, Zhilong Ji, Jinfeng Bai, Wangmeng Zuo

TL;DR
This paper introduces MDIQA, a multi-dimensional image quality assessment framework that models various perceptual dimensions to better reflect human visual evaluation and improve image restoration alignment.
Contribution
The paper presents a novel multi-dimensional IQA framework that captures diverse perceptual aspects and enables flexible image restoration training based on user preferences.
Findings
MDIQA outperforms existing IQA methods in accuracy.
The framework effectively guides image restoration to match perceptual preferences.
Extensive experiments validate the superior performance of MDIQA.
Abstract
Recent advancements in image quality assessment (IQA), driven by sophisticated deep neural network designs, have significantly improved the ability to approach human perceptions. However, most existing methods are obsessed with fitting the overall score, neglecting the fact that humans typically evaluate image quality from different dimensions before arriving at an overall quality assessment. To overcome this problem, we propose a multi-dimensional image quality assessment (MDIQA) framework. Specifically, we model image quality across various perceptual dimensions, including five technical and four aesthetic dimensions, to capture the multifaceted nature of human visual perception within distinct branches. Each branch of our MDIQA is initially trained under the guidance of a separate dimension, and the respective features are then amalgamated to generate the final IQA score.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
