On the performance of objective metrics for omnidirectional visual content

  title={On the performance of objective metrics for omnidirectional visual content},
  author={Evgeniy Upenik and Martin Rer{\'a}bek and Touradj Ebrahimi},
  journal={2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX)},
Omnidirectional image and video have gained popularity thanks to availability of capture and display devices for this type of content. [] Key Method The set is composed of four contents represented in two geometric projections and compressed with three different codecs at four different bitrates. A range of objective quality metrics for each stimulus is then computed and compared to subjective scores. Statistical analysis is performed in order to assess performance of each objective quality metric in…

Figures and Tables from this paper

Subjective and objective quality assessment of omnidirectional video

A subjective assessment campaign is conducted to evaluate the impact, on quality, of HEVC compression and/or spatial/temporal subsampling, when the videos are displayed in a head mounted device (HDM).

Assessing Visual Quality of Omnidirectional Videos

A new database is presented, which includes the viewing direction data from several subjects watching omnidirectional video sequences, and a subjective VQA method for measuring the difference mean opinion score (DMOS) of the whole and regional omnid Directional video, in terms of overall DMOS and vectorized DMOS, respectively.

Saliency Driven Perceptual Quality Metric for Omnidirectional Visual Content

This work proposes an objective metric to measure perceptual quality of omnidirectional visual content considering visual attention information and states that the non-deterministic impact must be addressed using statistical approach.

Voronoi-based Objective Quality Metrics for Omnidirectional Video

This paper proposes new objective metrics that take into account the unique aspects of ODV that are based on the subdivision of a given ODV into multiple patches using the spherical Voronoi diagram and introduces a new dataset of 75 impaired ODVs.

No-Reference Quality Assessment for 360-Degree Images by Analysis of Multifrequency Information and Local-Global Naturalness

This model is the first no-reference quality assessment method for 360-degree images that combines multifrequency information and image naturalness and outperforms state-of-the-art full-reference (FR) and NR approaches.

Quality Assessment of Super-Resolved Omnidirectional Image Quality Using Tangential Views

An objective, full-reference quality assessment framework which studies quality measurement for ODIs generated by GAN-based and CNN-based SISR methods is proposed and reveals that most objective metric show high performance over CNN based S ISR, while subjective tests favors Gan-based architectures.

Blind Omnidirectional Image Quality Assessment With Viewport Oriented Graph Convolutional Networks

This paper proposes a novel Viewport oriented Graph Convolution Network (VGCN) for blind omnidirectional image quality assessment (IQA) and demonstrates that the proposed model outperforms state-of-the-art full-reference and no-reference IQA metrics on two public omniddirectional IQA databases.

Deep Virtual Reality Image Quality Assessment With Human Perception Guider for Omnidirectional Image

The proposed deep networks consisting of virtual reality quality score predictor and human perception guider outperforms the existing two-dimentional image quality models and the state-of-the-art imagequality models for omnidirectional images.

Perceptual Analysis of Perspective Projection for Viewport Rendering in 360° Images

This study is based on subjective experiments conducted at Instituto Superior Técnico (IST), aiming to assess the perceptual impact of the rendering projection parameters, such as FoV and centre of projection, as well as the influence of the image content.

A Large-Scale Compressed 360-Degree Spherical Image Database: From Subjective Quality Evaluation to Objective Model Comparison

The experiment results reveal structure information, visual saliency information and compensation for geometric distortion are crucial for evaluating the quality of compressed 360-degree images.



Testbed for subjective evaluation of omnidirectional visual content

This paper introduces a testbed suitable for subjective evaluations of omnidirectional visual contents and shows the results of a conducted pilot experiment to illustrate the applicability of the proposed testbed.

Quality Assessment of Panorama Video for Videoconferencing Applications

New strategies for assessing the quality of composite video streams with specific emphasis on the following problems: noticeable calibration differences between adjacent cameras, concentration of motion in limited regions of the panoramic scene, combined vignetting problems, non-uniformity of the surfaces in the seam region between two adjacent cameras are presented.

A Framework to Evaluate Omnidirectional Video Coding Schemes

This paper extract viewport based head motion trajectories, and compares the original and coded videos on the viewport, and shows that the average viewport quality can be approximated by a weighted spherical PSNR.

Interactive omnidirectional video delivery: A bandwidth-effective approach

This paper evaluates the relevance and optimality of a personalized transmission where quality is modulated in spherical or cylindrical regions depending on their likelihood to be viewed during a live user interaction and shows how tiling and predictive methods can improve on existing methods.

Towards high efficiency video coding: Subjective evaluation of potential coding technologies

Quality metric for spherical panoramic video

This paper is dedicated to discussion of immersive media distribution format and quality estimation process and accuracy and reliability of the proposed objective quality estimation method had been verified with spherical panoramic images demonstrating good correlation results with subjective quality estimation held by a group of experts.

Geometry-driven quantization for omnidirectional image coding

A method to adapt the quantization tables of typical block-based transform codecs when the input to the encoder is a panoramic image resulting from equirectangular projection of a spherical image and results show that a rate reduction can be achieved for the same perceptual quality of the spherical signal with respect to a standard quantization.

Catadioptric omnidirectional camera

  • S. Nayar
  • Physics
    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1997
A new camera with a hemispherical field of view is presented and results are presented on the software generation of pure perspective images from an omnidirectional image, given any user-selected viewing direction and magnification.

Novel tile segmentation scheme for omnidirectional video

This paper proposes a tile based omnidirectional video segmentation scheme which can save up to 28% of pixel area and 20% of BD-rate averagely compared to the traditional equirectangular projection based approach.

Adaptive 360 VR Video Streaming: Divide and Conquer

This paper proposes a dynamic view-aware adaptation technique to tackle the huge bandwidth demands of 360 VR video streaming, and spatially divides the videos into multiple tiles, uses MPEG-DASH SRD to describe the spatial relationship of tiles in the 360-degree space, and constructs an efficient 3D geometry mesh called hexaface sphere to optimally represent a tiled 360VR video in the 3D space.