A Benchmark of DIBR Synthesized View Quality Assessment Metrics on a New Database for Immersive Media Applications

Abstract

Depth-Image-Based Rendering (DIBR) is a fundamental technology in several 3D-related applications, such as Free viewpoint video (FVV), Virtual Reality (VR) and Augmented Reality (AR). However, new challenges have also been brought in assessing the quality of DIBR-synthesized views since this process induces some new types of distortions, which are inherently different from the distortion caused by video coding. In this paper, we present a new DIBR-synthesized image database with the associated subjective scores. We also test the performances of the state-of-the-art objective quality metrics on this database. This work focuses on the distortions only induced by different DIBR synthesis methods. Seven state-of-the-art DIBR algorithms, including interview synthesis and single view based synthesis methods, are considered in this database. The quality of synthesized views was assessed subjectively by 41 observers and objectively using 14 state-of-the-art objective metrics. Subjective test results show that the interview synthesis methods, having more input information, significantly outperform the single view based ones. Correlation results between the tested objective metrics and the subjective scores on this database reveal that further studies are still needed for a better objective quality metric dedicated to the DIBR-synthesized views.

Quality Assessment for DIBR-Synthesized Images With Local and Global Distortions

“…We test the performance of the proposed method on IRCCyN/IVC [12], IETR [19], and MCL-3D [26] synthesized image databases. IRCCyN/IVC database is the first released benchmark database for DIBR synthesized image evaluation.…”

“…Zhou et al [18] proposed a quality index for the whole view synthesis based on the integration of Low-level and Mid-level Structural representation (LMS). Tian et al [19] focused on the distortions only induced by different DIBR synthesis methods and presented a new DIBR-synthesized image database with the associated subjective scores. Sandic-Stankovic et al [20] assumed that the perceived quality of DIBR-synthesized video can be estimated by quantifying the selected areas in the high-high wavelet subband, and proposed a new ast no-reference quality metric of synthesized video with synthesis distortions.…”

“…The abovementioned assessment metrics for synthesized images can be divided into three categories: local quality assessment (such as method in [12], [15] [19], [22]), global quality assessment (method in [13], [16], [18], [20]), and quality assessment combining local and global quality cues (method in [14], [17], [21]). For the performances of the local approaches, they are limited due to only considering the local distortion areas.…”

Quality Assessment of 3D Synthesized Images via Measuring Local Feature Similarity and Global Sharpness

“…In the experiment, three benchmark DIBR databases, including IRCCyN/IVC [9], IETR [16] and MCL-3D [15], are used for performance evaluation. All these databases contain reference views, the corresponding synthesized views obtained by different DIBR algorithms and the associated subjective rating scores.…”

“…To date, a number of objective quality assessment approaches [9]- [14] have been proposed for DIBR-synthesized images, and several publicly available databases [9], [15], [16] have been released. Although most of these specifically designed metrics for synthesized images perform better than traditional image quality assessment (IQA) metrics, their performance still has large room for improvement.…”