No-reference synthetic image quality assessment with convolutional neural network and local image saliency

作     者：Xiaochuan Wang Xiaohui Liang Bailin Yang Frederick W.B.Li 

作者机构：State Kay Laboratory of Virtual Reality Technology and SystemBeihang UniversityBeijing 100191China School of Computer Science&Information EngineeringZhejiang Gongshang UniversityHangzhou 310018China Department of Computer ScienceUniversity of DurhamUnited Kingdom 

出 版 物：《Computational Visual Media》 (计算可视媒体（英文版）)

年 卷 期：2019年第5卷第2期

页      面：193-208页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：sponsored by the National Key R&D Program of China (No. 2017YFB1002702) the National Natural Science Foundation of China (Nos. 61572058, 61472363) 

主　　题：image quality assessment synthetic image depth-image-based rendering(DIBR) convolutional neural network local image saliency 

摘      要：Depth-image-based rendering(DIBR) is widely used in 3 DTV, free-viewpoint video, and interactive 3 D graphics applications. Typically, synthetic images generated by DIBR-based systems incorporate various distortions, particularly geometric distortions induced by object dis-occlusion. Ensuring the quality of synthetic images is critical to maintaining adequate system service. However, traditional 2 D image quality metrics are ineffective for evaluating synthetic images as they are not sensitive to geometric distortion. In this paper, we propose a novel no-reference image quality assessment method for synthetic images based on convolutional neural networks, introducing local image saliency as prediction weights. Due to the lack of existing training data, we construct a new DIBR synthetic image dataset as part of our contribution. Experiments were conducted on both the public benchmark IRCCyN/IVC DIBR image dataset and our own dataset. Results demonstrate that our proposed metric outperforms traditional 2 D image quality metrics and state-of-the-art DIBR-related metrics.