Visual attention-aware quality estimation framework for omnidirectional video using spherical Voronoi diagram
- PDF / 3,818,339 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 15 Downloads / 203 Views
RESEARCH ARTICLE
Visual attention‑aware quality estimation framework for omnidirectional video using spherical Voronoi diagram Simone Croci1 · Cagri Ozcinar1 · Emin Zerman1 · Sebastian Knorr2 · Julián Cabrera3 · Aljosa Smolic1 Received: 1 December 2019 © Springer Nature Switzerland AG 2020
Abstract Omnidirectional video (ODV) enables viewers to look at every direction from a fixed point and provides a much more immersive experience than traditional 2D video. Assessing the video quality is important for delivering ODV to the enduser with the best possible quality. For this goal, two aspects of ODV should be considered. The first is the spherical nature of ODV and the related projection distortions when the ODV is stored in a planar format. The second is the interactive look-around consumption nature of ODV. Related to this aspect, visual attention, that identifies the regions that attract the viewer’s attention, is important for ODV quality assessment. Considering these aspects, in this paper, we study in particular objective full-reference quality assessment for ODV. To this end, we propose a quality assessment framework based on the spherical Voronoi diagram and visual attention. In this framework, a given ODV is subdivided into multiple planar patches with low projection distortions using the spherical Voronoi diagram. Afterwards, each planar patch is analyzed separately by a quality metric for traditional 2D video, obtaining a quality score for each patch. Then, the patch scores are combined based on visual attention into a final quality score. To validate the proposed framework, we create a dataset of ODVs with scaling and compression distortions, and conduct subjective experiments in order to gather the subjective quality scores and the visual attention data for our ODV dataset. The evaluation of the proposed framework based on our dataset shows that both the use of the spherical Voronoi diagram and visual attention are crucial for achieving state-of-the-art performance. Keywords Quality assessment · Omnidirectional video · 360° video · VR video · Spherical Voronoi diagram · Visual attention · Scaling distortion · Compression distortion * Simone Croci [email protected]
Introduction
Cagri Ozcinar [email protected]
Omnidirectional video (ODV), also known as 360° or VR video, can be conceived as a spherical video where the viewers are placed at its center, allowing them to look at every direction. ODV is ideally viewed with a head-mounted display (HMD) that shows only the content in the direction where the viewer is looking at. In contrast to traditional 2D video, this emerging media type provides higher immersive and interactive viewing experience. Thanks to its immersive nature, ODV can be used in different applications such as entertainment [1, 2], communication [3], health-care [4], and education [5]. Compared to traditional 2D video, ODV introduces new technical challenges especially for storage and transmission [3]. For example, due to the large field of view of ODV [6], higher video resolution i
Data Loading...
