提出多维度图像质量评估框架，让模型更贴近人类感知。
MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration
- 分技术与美学共九个维度建模图像质量
- 在多个数据集上超越现有方法表现
- 可灵活调整权重适配不同用户偏好
近年来，基于深度神经网络的图像质量评估（IQA）进展显著，提升了对人类视觉感知的逼近能力。然而，多数方法仅关注整体评分，忽略了人类在形成总体评价前会从多个维度进行判断的事实。为此，我们提出多维度图像质量评估（MDIQA）框架，将图像质量建模为五个技术维度和四个美学维度，在独立分支中分别训练，并融合各维度特征生成最终评分。该框架在完成训练后，可灵活用于图像恢复（IR）模型的训练，通过调节感知维度权重，使恢复结果更贴合用户偏好。大量实验表明，该方法在多个数据集上均优于现有方法，且能有效应用于图像恢复任务。代码已开源：https://github.com/YaoShunyu19/MDIQA。
原文摘要 · Abstract (English)
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. Additionally, when the MDIQA model is ready, we can deploy it for a flexible training of image restoration (IR) models, enabling the restoration results to better align with varying user preferences through the adjustment of perceptual dimension weights. Extensive experiments demonstrate that our MDIQA achieves superior performance and can be effectively and flexibly applied to image restoration tasks. The code is available: https://github.com/YaoShunyu19/MDIQA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。