Statistical Invariance for Texture Synthesis
Publication in refereed journal


摘要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.
著者Liu XP, Jiang L, Wong TT, Fu CW
期刊名稱IEEE Transactions on Visualization and Computer Graphics
出版社Institute of Electrical and Electronics Engineers (IEEE)
頁次1836 - 1848
關鍵詞illumination and deformation estimation; statistical invariance; Texture synthesis
Web of Science 學科類別Computer Science; Computer Science, Software Engineering; COMPUTER SCIENCE, SOFTWARE ENGINEERING

上次更新時間 2020-17-10 於 00:54