Quality assessment of DIBR-synthesized views: An overview

NEUROCOMPUTING

卷:423

Article

Tian, Shishun^1,2  Zhang, Lu^3,4  Zou, Wenbin^1,2  Li, Xia^1,2  Su, Ting⁵  Morin, Luce^3,4  Deforges, Olivier^3,4 

[1] Shenzhen Univ, Coll Elect & Informat Engn, Shenzhen 518060, Peoples R China

[2] Shenzhen Univ, Guangdong Prov Key Lab Intelligent Informat Proc, Shenzhen 518060, Peoples R China

[3] INSA Rennes, Natl Inst Appl Sci Rennes, Rennes, France

[4] IETR Inst Elect & Technol NumR, CNRS, UMR 6164, Rennes, France

[5] Chinese Acad Sci, Shenzhen Inst Adv Technol, Res Ctr Med Articial Intelligence, Shenzhen 518055, Guangdong, Peoples R China

关键词: DIBR;    Multi-view videos (MVV);    View synthesis;    Distortions;    Quality assessment;   

DOI  :  10.1016/j.neucom.2020.09.062

来源: Elsevier

【 摘 要 】

The Depth-Image-Based-Rendering (DIBR) is one of the main fundamental technique to generate new views in 3D video applications, such as Multi-View Videos (MVV), Free-Viewpoint Videos (FVV) and Virtual Reality (VR). However, the quality assessment of DIBR-synthesized views is quite different from the traditional 2D images/videos. In recent years, several efforts have been made towards this topic, but there is a lack of detailed survey in the literature. In this paper, we provide a comprehensive survey on various current approaches for DIBR-synthesized views. The current accessible datasets of DIBR-synthesized views are firstly reviewed, followed by a summary analysis of the representative state-of-the-art objective metrics. Then, the performances of different objective metrics are evaluated and discussed on all available datasets. Finally, we discuss the potential challenges and suggest possible directions for future research. (c) 2020 Elsevier B.V. All rights reserved.

【 授权许可】

Free