Re-visiting discriminator for blind free-viewpoint image quality assessment

Ling, Suiyi, Li, Jing, Che, Zhaohui, Zhou, Wei, Wang, Junle and Le Callet, Patrick 2021. Re-visiting discriminator for blind free-viewpoint image quality assessment. IEEE Transactions on Multimedia 23 , pp. 4245-4258. 10.1109/TMM.2020.3038305

Full text not available from this repository.

Abstract

Accurate measurement of perceptual quality is important for various immersive multimedia, which demand real-time quality control or quality-based bench-marking for relevant algorithms. For instance, virtual views rendering in Free-Viewpoint (FV) navigation scenarios is a typical case that introduces challenging distortions, particularly the ones around dis-occluded regions. Existing quality metrics, most of which are targeting for impairments caused by compression or network condition, fail to quantify such non-uniform structure-related distortions. Moreover, the lack of quality databases for such distortions makes it even more challenging to develop robust quality metrics. In this work, a Generative Adversarial Networks based No-Reference (NR) quality Metric, namely GANs-NRM, is proposed. We first present an approach to create masks mimicking dis-occlusions/textureless regions, which is applicable on large-scale 2D image databases publicly available in the computer vision domain. Using these synthetic data, we then train a GANs-based context renderer with the capability of rendering those masked regions. Since the naturalness of the rendered dis-occluded regions strongly relates to the perceptual quality, we assume that the discriminator of the trained GANs has an intrinsic ability for quality assessment. We thus use the features extracted from the discriminator to learn a Bag-of-Distortion-Word (BDW) codebook. We show that a quality predictor can be then well trained using only a small amount of subjective quality data for the FV views rendering. Moreover, in the proposed framework, the discriminator is also adapted as a distortion-detector to locate possible distorted regions. According to the experimental results, the proposed model outperforms significantly the state-of-the-art quality metrics. The corresponding context renderer also shows appealing visualized results over other rendering algorithms.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1520-9210
Date of Acceptance:	2 November 2020
Last Modified:	21 Aug 2023 16:15
URI:	https://orca.cardiff.ac.uk/id/eprint/161685

Actions (repository staff only)

Edit Item