Learning to Predict Localized Distortions in Rendered Images

Learning to Predict Localized Distortions in Rendered Images
复制标题

学习预测渲染图像中的局部失真

DOI:
10.1111/cgf.12248
复制
发表时间:
2013
影响因子:
2.5
通讯作者:
Cadík M
Cadík M
中科院分区:
计算机科学4区
文献类型:
--
作者:
Cadík M

文献摘要

参考文献

被引文献

相似文献

在这项工作中,我们提出了用于客观图像质量评估的特征描述符分析。我们探索了大量可能的特征,包括现有图像质量指标的组成部分以及许多传统的计算机视觉和统计特征。此外,我们提出了受人类感知启发的新功能,并分析了在用户实验中使用眼动仪获取的视觉显着性图。通过机器学习框架评估特征的判别力,揭示每个特征对于图像质量评估任务的重要性。此外,我们提出了一种新的数据驱动的全参考图像质量指标,其性能优于当前最先进的指标。该指标是根据结合两个公开可用数据集的主观真实数据进行训练的。为了完整起见,我们创建了一个新的测试合成数据集,包括实验测量的主观失真图。最后,使用相同的机器学习框架,我们优化了流行的现有指标的参数。
In this work, we present an analysis of feature descriptors for objective image quality assessment. We explore a large space of possible features including components of existing image quality metrics as well as many traditional computer vision and statistical features. Additionally, we propose new features motivated by human perception and we analyze visual saliency maps acquired using an eye tracker in our user experiments. The discriminative power of the features is assessed by means of a machine learning framework revealing the importance of each feature for image quality assessment task. Furthermore, we propose a new data‐driven full‐reference image quality metric which outperforms current state‐of‐theart metrics. The metric was trained on subjective ground truth data combining two publicly available datasets. For the sake of completeness we create a new testing synthetic dataset including experimentally measured subjective distortion maps. Finally, using the same machine‐learning framework we optimize the parameters of popular existing metrics.
DOI: --
发表时间: 1984
期刊:
影响因子: --
作者:
H. Widdel
通讯作者: H. Widdel
DOI: 10.1145/2366145.2366166
发表时间: 2012-11-01
影响因子: 6.2
作者:
Cadik, Martin;Herzog, Robert;Seidel, Hans-Peter
通讯作者: Seidel, Hans-Peter
K.Hiromi:Elsevier Science Publishers B.V.(阿姆斯特丹)。
DOI: --
发表时间: --
期刊:
影响因子: --
作者:
通讯作者: --