PQA-Net: Deep No Reference Point Cloud Quality Assessment via Multi-View Projection

• Published in: IEEE transactions on circuits and systems for video technology Vol. 31; no. 12; pp. 4645 - 4660
• Main Authors: Liu, Qi, Yuan, Hui, Su, Honglei, Liu, Hao, Wang, Yu, Yang, Huan, Hou, Junhui
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Communications systems; deep neural network; Distortion; Feature extraction; Forecasting; Geometry; Image color analysis; Learning systems; Machine learning; Measurement; Modules; multi-task learning; multi-view; Multitasking; No-reference point cloud quality assessment; Point cloud compression; Quality assessment; Three dimensional models; Three-dimensional displays

Recently, 3D point cloud is becoming popular due to its capability to represent the real world for advanced content modality in modern communication systems. In view of its wide applications, especially for immersive communication towards human perception, quality metrics for point clouds are essent...