As part of the TRANSMIXR work on metrics and evaluation, the Distributed and Interactive Systems (DIS) group from CWI presented the work “Evaluation of point cloud features for no-reference visual quality assessment” at the IEEE International Conference on Quality of Multimedia Experience (QoMEX) 2023.
With the rise of immersive XR applications, there is a growing interest in high-fidelity representations of real-world objects and scenes, particularly point clouds. The research work explores the use of full-reference features for assessing the quality of point cloud contents in a no-reference framework. The study evaluates various features commonly employed in full-reference point cloud quality assessment and tests their performance in predicting quality without a reference. The results demonstrate the potential of full-reference features for no-reference assessment, indicating their effectiveness even in the absence of a reference. The findings encourage further exploration and development of point cloud quality metrics using different features and machine learning techniques.
The work presented at QoMEX 2023, complements other point cloud quality metrics proposed by the CWI team, including Hist_Y (a Full-Reference metric based on luminance histograms), PCM_RR (A Reduced-Reference metric based on global features from location, color and normals), and PointPCA (a Full-Reference metric based on statistical moments of geometric descriptions after Principal Component Analysis and luminance intensities). The last one was recently extended, as PointPCA+, for a successful participation (finalists in the three tracks where the researchers participated) in the competitive Grand Challenge “Point Cloud Visual Quality Assessment” from the IEEE International Conference on Image Processing (IEEE ICIP). A summary of all the efforts of DIS on point cloud objective metrics from can be found here: https://www.dis.cwi.nl/point-cloud-objective-quality-metrics/.
In addition, Ashutosh Singla, a former researcher at TU Ilmenau, had the opportunity to present his research work at QoMEX 2023. He is Currently employed in the TransMIXR project at CWI.
Scientific article:
- G. Smitskamp, I. Viola, and P. Cesar., “Evaluation of point cloud features for no-reference visual quality assessment”, QoMEX 2023, Ghent, Belgium.