Parametric quality assessment of synthesized textures

In this paper, we present the results of a study designed to investigate the visual factors which contribute to the perceived quality of synthesized textures. A psychophysical experiment was performed in which subjects rated the quality of textures synthesized from a variety of modern texture-synthesis algorithms. The ratings were given in terms of how well each synthesized texture represented a sample from the same material from which the original texture was obtained. The results revealed that the most detrimental artifact was lack of structural details. Other pronounced artifacts included: (1) misalignment of the texture patterns; (2) blurring introduced in the texture patterns; and (3) repeating the same patch again and again (tiling). Based on these results, we present an analysis of the efficacy of various measureable parameters at predicting the ratings. We show how a linear combination of the parameters from a parametric texture-synthesis algorithm demonstrates better performance at predicting the ratings compared to traditional quality-assessment algorithms. 1