2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDSMR-2.3
Paper Title A REDUCED REFERENCE METRIC FOR VISUAL QUALITY EVALUATION OF POINT CLOUD CONTENTS
Authors Irene Viola, Pablo Cesar, Centrum Wiskunde & Informatica (CWI), Netherlands
SessionSMR-2: Perception and Quality Models
LocationArea F
Session Time:Wednesday, 22 September, 14:30 - 16:00
Presentation Time:Wednesday, 22 September, 14:30 - 16:00
Presentation Poster
Topic Three-Dimensional Image and Video Processing: Point cloud processing
Abstract Point cloud representation has seen a surge of popularity in recent years, thanks to its capability to reproduce volumetric scenes in immersive scenarios. New compression solutions for streaming of point cloud contents have been proposed, which require objective quality metrics to reliably assess the level of degradation introduced by coding and transmission distortions. In this context, reduced reference metrics aim to predict the visual quality of the transmitted contents, while requiring only a small set of features to be sent in addition to the streamed media. In this paper, we propose a reduced reference metric to predict the quality of point cloud contents under compression distortions. To do so, we extract a small set of statistical features from the reference point cloud in the geometry, color and normal vector domain, which can be used at the receiver side to assess the visual degradation of the content. Using publicly available ground-truth datasets, we compare the performance of our metric to widely-used full reference metrics. Results demonstrate that our metric is able to effectively predict the level of distortion in the degraded point cloud contents, achieving high correlation values with respect to subjective scores.