No-reference synthetic image quality assessment with convolutional neural network and local image saliency

Wang, Xiaochuan; Liang, Xiaohui; Yang, Bailin; Li, Frederick W.B.

Abstract

Depth-image-based rendering (DIBR) is widely used in 3DTV, free-viewpoint video, and interactive 3D graphics applications. Typically, synthetic images generated by DIBR-based systems incorporate various distortions, particularly geometric distortions induced by object dis-occlusion. Ensuring the quality of synthetic images is critical to maintaining adequate system service. However, traditional 2D image quality metrics are ineffective for evaluating synthetic images as they are not sensitive to geometric distortion. In this paper, we propose a novel no-reference image quality assessment method for synthetic images based on convolutional neural networks, introducing local image saliency as prediction weights. Due to the lack of existing training data, we construct a new DIBR synthetic image dataset as part of our contribution. Experiments were conducted on both the public benchmark IRCCyN/IVC DIBR image dataset and our own dataset. Results demonstrate that our proposed metric outperforms traditional 2D image quality metrics and state-of-the-art DIBR-related metrics.

Citation

Wang, X., Liang, X., Yang, B., & Li, F. W. (2019). No-reference synthetic image quality assessment with convolutional neural network and local image saliency. Computational Visual Media, 5(2), 193-208. https://doi.org/10.1007/s41095-019-0131-6

• Journal Article Type: Article
• Acceptance Date: Jan 27, 2019
• Online Publication Date: Mar 30, 2019
• Publication Date: Jun 1, 2019
• Deposit Date: Jul 12, 2019
• Publicly Available Date: Jul 12, 2019
• Journal: Computational Visual Media
• Print ISSN: 2096-0433
• Electronic ISSN: 2096-0662
• Publisher: SpringerOpen
• Peer Reviewed: Peer Reviewed
• Volume: 5
• Issue: 2
• Pages: 193-208
• DOI: https://doi.org/10.1007/s41095-019-0131-6
• Public URL: https://durham-repository.worktribe.com/output/1292541