摘要 : The Depth-Image-Based-Rendering (DIBR) is one of the main fundamental technique to generate newviews in 3D video applications, such as Multi-View Videos (MVV), Free-Viewpoint Videos (FVV) andVirtual Reality (VR). However, the qual... 展开 The Depth-Image-Based-Rendering (DIBR) is one of the main fundamental technique to generate newviews in 3D video applications, such as Multi-View Videos (MVV), Free-Viewpoint Videos (FVV) andVirtual Reality (VR). However, the quality assessment of DIBR-synthesized views is quite different fromthe traditional 2D images/videos. In recent years, several efforts have been made towards this topic, butthere is a lack of detailed survey in the literature. In this paper, we provide a comprehensive surveyon various current approaches for DIBR-synthesized views. The current accessible datasets ofDIBR-synthesized views are firstly reviewed, followed by a summary analysis of the representativestate-of-the-art objective metrics. Then, the performances of different objective metrics are evaluatedand discussed on all available datasets. Finally, we discuss the potential challenges and suggest possibledirections for future research. 收起