Video and image quality assessment has long been projected as a regression problem, which requires predicting a continuous quality score given an input stimulus. However, recent efforts have shown that accurate quality score regression on real-world user-generated content (UGC) is a very challenging task. To make the problem more tractable, we propose two new methods - binary, and ordinal classification - as alternatives to evaluate and compare no-reference quality models at coarser levels. Moreover, the proposed new tasks convey more practical meaning on perceptually optimized UGC transcoding, or for preprocessing on media processing platforms. We conduct a comprehensive benchmark experiment of popular no-reference quality models on recent in-the-wild picture and video quality datasets, providing reliable baselines for both evaluation methods to support further studies. We hope this work promotes coarse-grained perceptual modeling and its applications to efficient UGC processing.
Dilated convolutional neural network-based deep reference picture generation for video compression
Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Science and Technology on Electro-optic Control Laboratory(光电控制技术重点实验室);Charles Sturt University(查尔斯特大学)
Local Structure Matching Driven by Joint-Saliency-Structure Adaptive Kernel Regression
Shanghai Jiao Tong University(上海交通大学);University College London(伦敦大学学院);Shanghai Renji Hospital, School of Medicine, Shanghai Jiaotong University(上海交通大学医学院附属上海仁济医院);University of the West of England(西英格兰大学)
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)
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。
Analyzing Near-Infrared Hyperspectral Imaging for Protein Content Regression and Grain Variety Classification Using Bulk References and Varying Grain-to-Background Ratios
University of Copenhagen(哥本哈根大学);FOSS Analytical A/S(福斯分析仪器公司)
Bidirectional Regression for Monocular 6DoF Head Pose Estimation and Reference System Alignment
Department of Electronics and Communications Engineering, Kwangwoon University(韩国 Kwangwoon 大学电子与通信工程系);Department of Software Engineering, Dankook University(韩国 Dankook 大学软件工程系);School of Computer Science, University of Birmingham(英国 Birmingham 大学计算机科学学院)