Interactive Object Surface Retexturing using Perceptual Quality Indexes

Abstract

This paper presents an intuitive retexturing system for editing object surfaces in images interactively. In the conventional retexturing methods, users were required to select texture images from a texture database. On the other hands, our system requires users to respond intuitive terms of material perception. Then, based on the user response, an optimal texture image is selected for the retexturing. For calculating an optimal texture image, we develop a material texture database with perceptual quality scores. The database is constructed on the basis of our subjective experiments with nine perceptual quality indexes which were suggested by Fleming et al. (2013). In the actual retexturing system, first, a user captures or selects an image including a retexturing target. Second, a target object region is extracted by Lazy Snapping which is an interactive image segmentation technique. Third, as to represent a target surface, the user sets the perceptual quality parameters and preferred object materials. Then, based on the user settings, an optimal texture is calculated from our material texture database. Finally the user achieves a retextured object image by adopting the optimal texture. For realizing interactive retexturing system, we have implemented our algorithm on tablet computers with Android and Windows OSs.