Please wait a minute...
Vis Inf
Vis Inf  2021, Vol. 5 Issue (1): 67-75    DOI: 10.1016/j.visinf.2021.02.004
论文     
基于稀疏表示的深度图像质量评估
Dorsaf Seba, Maryem Sehli, Faouzi Ghorbel
National School of Computer Sciences, University of Manouba, Tunisia
Sparse Representations-based depth images quality assessment
Dorsaf Sebai, Maryem Sehli, Faouzi Ghorbel
National School of Computer Sciences, University of Manouba, Tunisia
 全文: PDF 
摘要： 常规的2D度量可用来评测深度图的质量，但是当被用于评估3D质量时，却是低效和不准确的。本文提出了一种新的全参考目标度量，称为“稀疏表示-均方误差（SR-MSE）”，该度量可有效地评估深度图压缩失真。它在专用于深度特征的混合冗余变换域中自适应地对参考深度图和压缩深度图进行建模。然后，它计算该模型中的稀疏系数之间的均方误差。作为质量评估的基准，本文在不同比特率情况下，使用最新3D高效视频编码标准对压缩的深度图进行了主观评估测试，并将主观评估结果与本文建议的和常规的两种客观指标进行了比较。实验结果表明，与常规图像质量评估指标相比，本文方法的结果与主观评分最为接近。
关键词： 深度图;  稀疏表示;  转换域;  图像质量评估;  3D-HEVC    
Abstract: The conventional 2D metrics can be used for measuring the quality of depth maps, but none of them is considered to be efficient and is not accurate when used for evaluating 3D quality. In this paper, we propose a new full reference objective metric, called Sparse Representations-Mean Squared Error (SR-MSE), which efficiently evaluates the depth maps compression distortions. It adaptively models the reference and compressed depth maps in a mixed redundant transform domain dedicated to depth features. Then, it computes the mean squared error between the sparse coefficients issued from this modeling. As a benchmark of quality assessment, we perform a subjective evaluation test for depth maps compressed using the latest 3D High Efficiency Video Coding standard at various bitrates. We compare the subjective results with the proposed and conventional objective metrics. Experimental results demonstrate that the proposed SR-MSE, compared to the conventional image quality assessment metrics, yields the highest correlated scores to the subjective ones.
Key words: Depth maps    Sparse representations    Transform domain    Image Quality Assessment    3D-HEVC
出版日期: 2021-04-08
通讯作者: Dorsaf Sebai     E-mail: dorsaf.sebai@ensi-uma.tn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Dorsaf Sebai
Maryem Sehli
Faouzi Ghorbel

引用本文:

Dorsaf Sebai, Maryem Sehli, Faouzi Ghorbel. Sparse Representations-based depth images quality assessment. Vis Inf, 2021, 5(1): 67-75.

链接本文:

http://www.zjujournals.com/vi/CN/10.1016/j.visinf.2021.02.004    或    http://www.zjujournals.com/vi/CN/Y2021/V5/I1/67

No related articles found!