Highly Efficient Quality Assessment of 3D-Synthesized Views Based on Compression Technology

Image quality assessment (IQA) technology is facing a new challenge due to the large amount of demand for high-quality 3-D-synthesized views stimulated by the rapid development of virtual reality applications. Since 3-D synthesis views commonly rely on the depth-image-based rendering technology to synthesize virtual images (without reference images in reality and containing geometric distortion), only the no-reference (NR) quality assessment method can meet the requirements. However, most of the current IQA methods for 3-D-synthesized views are full-reference methods. So far, only one specialized NR IQA method for 3-D-synthesized views has been proposed, but its computation is too expensive. For this reason, we have previously proposed a method for extracting geometric distortion regions using the Joint Photographic Experts Group (JPEG) image compression technology to evaluate image quality. In this paper, we consider that although heavy JPEG compression can effectively extract the geometric distortion area, it will ignore the image quality degradation caused by other distortions. Therefore, we have improved our previous work to extract geometric distortions and non-geometric distortions by high-level JPEG compression and lowlevel JPEG compression, respectively. The overall image quality score was obtained by the fusion of the two results. Experiments indicate that the proposed blind quality model is superior to modern full-, reduced-, and no-reference methods. Compared with our previous work, the performance of the new algorithm has been greatly improved. At the same time, compared with the existing dedicated NR IQA method, the performance is similar but the calculation speed has obvious advantages.