Subscribe

Issue No.11 - Nov. (2012 vol.18)

pp: 1836-1848

Xiaopei Liu , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore

Lei Jiang , Tencent Inc., Shenzhen, China

Tien-Tsin Wong , Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, Shatin, China

Chi-Wing Fu , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TVCG.2012.75

ABSTRACT

Estimating illumination and deformation fields on textures is essential for both analysis and application purposes. Traditional methods for such estimation usually require complicated and sometimes labor-intensive processing. In this paper, we propose a new perspective for this problem and suggest a novel statistical approach which is much simpler and more efficient. Our experiments show that many textures in daily life are statistically invariant in terms of colors and gradients. Variations of such statistics can be assumed to be influenced by illumination and deformation. This implies that we can inversely estimate the spatially varying illumination and deformation according to the variation of the texture statistics. This enables us to decompose a texture photo into an illumination field, a deformation field, and an implicit texture which are illumination- and deformation-free, within a short period of time, and with minimal user input. By processing and recombining these components, a variety of synthesis effects, such as exemplar preparation, texture replacement, surface relighting, as well as geometry modification, can be well achieved. Finally, convincing results are shown to demonstrate the effectiveness of the proposed method.

INDEX TERMS

statistical analysis, image texture, geometry modification, statistical invariance, texture synthesis, labor-intensive processing, novel statistical approach, deformation, illumination, texture statistics, texture photo, exemplar preparation, texture replacement, surface relighting, Lighting, Image color analysis, Estimation, Surface texture, Geometry, Tensile stress, Surface reconstruction, illumination and deformation estimation, Texture synthesis, statistical invariance

CITATION

Xiaopei Liu, Lei Jiang, Tien-Tsin Wong, Chi-Wing Fu, "Statistical Invariance for Texture Synthesis",

*IEEE Transactions on Visualization & Computer Graphics*, vol.18, no. 11, pp. 1836-1848, Nov. 2012, doi:10.1109/TVCG.2012.75REFERENCES