Tensor Oriented No-Reference Light Field Image Quality Assessment

Light field image (LFI) quality assessment is becoming more and more important, which helps to better guide the acquisition, processing and application of immersive media. However, due to the inherent high dimensional characteristics of LFI, the LFI quality assessment turns into a multi-dimensional problem that requires consideration of the quality degradation in both spatial and angular dimensions. Therefore, we propose a novel Tensor oriented No-reference Light Field image Quality evaluator (Tensor-NLFQ) based on tensor theory. Specifically, since the LFI is regarded as a low-rank 4D tensor, the principal components of four oriented sub-aperture view stacks are obtained via Tucker decomposition. Then, the Principal Component Spatial Characteristic (PCSC) is designed to measure the spatial-dimensional quality of LFI considering its global naturalness and local frequency properties. Finally, the Tensor Angular Variation Index (TAVI) is proposed to measure angular consistency quality by analyzing the structural similarity distribution between the first principal component and each view in the view stack. Extensive experimental results on four publicly available LFI quality databases demonstrate that the proposed Tensor-NLFQ model outperforms state-of-the-art 2D, 3D, multi-view, and LFI quality assessment algorithms.

I. Introduction

As an important medium for human visual perception, light enables humans to effectively perceive the spatial, color, form and dynamic changes of our environment. Conventional media modalities such as 2D images mainly consider the intensity information of radiance, which can only provide a two-dimensional (2D) sense of presence. Different from traditional image capturing formats, light field content records both radiation intensity and direction information of light rays in the free space, thus providing an enhanced immersive experience. Considering the abundant spatial and angular information of the light field, its processing and application have attracted widespread attention in past decades. However, these operations inevitably introduce heterogeneous artifacts, resulting in the degradation of the perceptual quality for light field content [1]. Therefore, monitoring the perceptual quality of light field content is critical to better guiding the procedure of light field acquisition, processing and application techniques.