Blind 3D-Synthesized Image Quality Measurement by Analysis of Local and Global Statistical Properties

• Published in: IEEE transactions on instrumentation and measurement 2023-01, Vol.72, p.1-1
• Main Authors: Fang, Zhewei, Cui, Yueli, Yu, Mei, Jiang, Gangyi, Lian, Kaiyin, Wen, Yulu, Xu, Jiayao
• Format: Article
• Language: English
• Subjects: 3D-synthesized image; Blurring; Distortion; Distortion measurement; Entropy; Feature extraction; fractal dimension map; Fractal geometry; Image quality; Kernel; Measurement; Prediction models; Quality assessment; Regression models; Statistical analysis; steerable pyramid decomposition; Synthesis; Texture; two-dimensional entropy; Visual quality measurement; Visualization
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2023.3306527

Depth-Image-Based-Rendering (DIBR) procedure aims to create virtual viewpoint using the adjacent viewpoints and the corresponding depth maps for free-viewpoint video applications. However, this processing inevitably introduces visual artifacts which differ from those of natural images, mainly including holes, stretching, and blurring. To accurately evaluate the quality of 3D-synthesized images, a robust blind metric is developed by analysis of Local and Global Statistical Properties (LGSP). On the one hand, for local features, since the DIBR processing tends to damage the amount of information at the disoccluded regions in 3D-synthesized images, we extract the local two-dimensional entropy features from the spatial domain and log-Gabor domain guided by the corresponding saliency map to measure local information variation. Moreover, local statistical features are extracted from fractal dimension maps to capture local texture variations due to significant local texture degradation engendered by the DIBR procedure. On the other hand, for global features, to measure the DIBR-induced geometric distortion, steerable pyramid decomposition is utilized to extract its cross-scale and cross-orientation joint statistical features. Meanwhile, log-energies features are extracted from multi-scale and multi-orientation wavelet subbands to characterize its global blurring. Finally, the combined local and global quality-aware features are utilized to train the quality prediction model using regression function to establish the mapping between visual features and subjective scores. Extensive experiments over three public 3D-synthesized image benchmark databases show that our metric outpaces the newly-developed 3D-synthesized image metrics and the popular 2D image metrics.