arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1612.01697cs.CV
收藏

用于无参考和全参考图像质量评估的深度神经网络

Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment

Fraunhofer Heinrich Hertz Institute (Fraunhofer HHI)(弗劳恩霍夫海因里希·赫兹研究所);Berlin Institute of Technology(柏林工业大学)

Sebastian Bosse, Dominique Maniry, Klaus-Robert Müller, Thomas Wiegand, Wojciech Samek

摘要:

我们提出了一种基于深度神经网络的图像质量评估(IQA)方法。该网络是端到端训练的,包括10个卷积层和5个用于特征提取的池化层,以及两个用于回归的全连接层,这使得它比相关的IQA模型更深入。所提出的架构的独特特征在于:1)通过轻微的调整,它可以用于无参考(NR)以及全参考(FR)IQA设置中,以及2)它允许局部质量和局部权重的联合学习,即,在一个统一的框架内,局部质量对整体质量估计的相对重要性。我们的方法纯粹是数据驱动的,不依赖于手工制作的功能或其他类型的关于人类视觉系统或图像统计的先验领域知识。我们在LIVE,CISQ和TID 2013数据库以及LIVE In Wild图像质量挑战数据库上评估了所提出的方法,并显示出优于最先进的NR和FR IQA方法的性能。最后,跨数据库评估显示出在不同数据库之间进行概括的高能力,表明所学习的特征具有高鲁棒性。

英文摘要:

We present a deep neural network-based approach to image quality assessment (IQA). The network is trained end-to-end and comprises ten convolutional layers and five pooling layers for feature extraction, and two fully connected layers for regression, which makes it significantly deeper than related IQA models. Unique features of the proposed architecture are that: 1) with slight adaptations it can be used in a no-reference (NR) as well as in a full-reference (FR) IQA setting and 2) it allows for joint learning of local quality and local weights, i.e., relative importance of local quality to the global quality estimate, in an unified framework. Our approach is purely data-driven and does not rely on hand-crafted features or other types of prior domain knowledge about the human visual system or image statistics. We evaluate the proposed approach on the LIVE, CISQ, and TID2013 databases as well as the LIVE In the wild image quality challenge database and show superior performance to state-of-the-art NR and FR IQA methods. Finally, cross-database evaluation shows a high ability to generalize between different databases, indicating a high robustness of the learned features.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑