Light Field Image Quality Assessment Using Natural Scene Statistics and Texture Degradation

Ma, Jian; Zhang, Xiaoyin; Cheng, Jie-Zhi; An, Ping; Xu, G. S.

doi:10.1109/tcsvt.2023.3297016

Cited by 7 publications

(1 citation statement)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The FR/RR LFIQA metrics [38], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53] evaluate the perceptual quality of distorted LFIs by using the full/partial reference information. For example, Fang et al [43] propose a FR LFIQA metric by calculating the similarity between the gradient magnitudes of reference and distorted SAIs and EPIs.…”

Section: B Quality Assessment Of Lfismentioning

confidence: 99%

Blind Perceptual Quality Assessment of LFI Based on Angular-Spatial Effect Modeling

Zhang,

Tian,

Zhang

et al. 2024

IEEE Trans. on Broadcast.

View full text Add to dashboard Cite

By recording scenes from multiple viewpoints, Light Field Image (LFI) encompasses both angular and spatial information, thereby offering users a more immersive experience. Since LFIs may be distorted at various stages from acquisition to visualization, Light Field Image Quality Assessment (LFIQA) is of vitally important to monitor the potential impairments of LFI quality. However, existing objective LFIQA metrics fail to establish a reasonable correlation between spatial and angular information in LFIs, especially ignoring the imbalance problem of large spatial variations and subtle angular variations, which results in unsatisfactory quality evaluation performance. To alleviate this imbalance, in this paper, we propose a novel Blind LFIQA metric based on Angular-Spatial Effect Modeling, abbreviated as ASEM-BLiF. Specifically, the proposed metric consists of two branches. In the principal branch, we first present an Angular Effect Modeling (AEM) module to capture the angular information independently of spatial information. Based on AEM, we further design an Angular-Spatial Quality Learning (ASQL) module to model the local angular-spatial effect and establish the global relationship between different local regions for quality assessment via Transformer. In the auxiliary branch, a Discriminative Region Selection (DRS) module is proposed for auxiliary learning to improve the learning efficiency and prediction accuracy from a local perspective. Moreover, we present a Dynamic Weighting Loss (DWLoss) to achieve an optimal balance between principal and auxiliary learning throughout training. To demonstrate the effectiveness of the proposed metric, extensive experiments are conducted on five publicly available LFIQA databases with a variety of metrics.The experimental results show that compared to our previous work DeeBLiF, the current state-of-the-art LFIQA metric, our proposed ASEM-BLiF metric achieves 5.67%, 7.75%, 5.96%, 4.44%, and 0.33% SROCC performance improvements in quality assessment on the Win5-LID, NBU-LF1.0, LFDD, VALID10bit, and SHU databases, respectively. The code will be publicly available.

show abstract