Quality assessment of DIBR-synthesized views: An overview

S. Tian (1) , Lu Zhang (2) , W. Zou (1) , Xiaojian Li (1) , T. Su (3) , Luce Morin (2) , O. Déforges (2)

1 Shenzhen University [Shenzhen]
2 IETR - Institut d'Électronique et des Technologies du numéRique
3 SIAT - Shenzhen Institutes of Advanced Technology

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.

Mots clés: DIBR; Distortions; Multi-view videos (MVV); Quality assessment; View synthesis

Domaines: Sciences de l'ingénieur [physics]

S. Tian, Lu Zhang, W. Zou, Xiaojian Li, T. Su, et al.. Quality assessment of DIBR-synthesized views: An overview. Neurocomputing, 2021, 423, pp.158-178. ⟨10.1016/j.neucom.2020.09.062⟩. ⟨hal-03040344⟩