An in-depth analysis of single-image subjective quality assessment of light field contents

Quality assessment of light field images poses new questions and challenges, due to the enriched nature of the content and the possibilities it offers at the rendering step. Image-based rendering is conventionally used to showcase the increased capabilities of light field contents on traditional 2D screens. However, the range of possibilities for rendering parameters is virtually endless, which poses the problem of what rendered images should be used when performing visual quality assessments, as well as how to properly present them to subjects during quality evaluations. Single-image assessment has been used in the past to conduct subjective quality evaluations. Since this type of assessment generates a large number of stimuli to be evaluated, which increases the complexity, length, and cost of the test, it is fundamental to analyze whether the added strain on the evaluation procedure is compensated by statistically relevant results. In this paper, we analyze the results of a subjective evaluation campaign that used single-image assessment by means of statistical tools, to understand whether the advantages of evaluating light field contents through separately rendered images counterbalance the increase in complexity. In particular, we test whether different types of rendering lead to statistically different ratings, and if testing a variety of rendering parameters through single-image assessment is advisable. Results provide useful guidelines to designs more efficient subjective quality assessment for light field contents.