3D Surface Texture Synthesis Using Wavelet Coefficient Fitting

Abstract

Texture synthesis is widely used in virtual reality and computer games and has become one of the most active research areas. Research into texture synthesis is normally concerned with generation of 2D images of texture. However, real-world surface textures comprise rough surface geometry and various reflectance properties. These surface textures are different from 2D still texture as their images can therefore vary dramatically with illumination directions. This paper presents a simple framework for 3D surface texture synthesis. Firstly, we propose a novel 2D texture synthesis algorithm based on wavelet transform that can be efficiently extended to synthesis surface representations in multi-dimensional space. The proposed texture synthesis method can avoid joint seams during synthesis by first fitting wavelet coefficients in the overlap texture images, and then performing an inverse wavelet transform to generate new textures. Then, Photometric Stereo (PS) is used to generate surface gradient and albedo maps from three synthesized surface texture images. The surface gradient maps can be further integrated to produce a surface height map (surface profile). With the albedo and height or gradient maps, new images of a Lambertian surface under arbitrary illuminant directions can be generated. Experiments show that the proposed approach can not only produce 3D surface textures under arbitrary illumination directions, but also have the ability to retain the surface geometry structure.