Journal of Computer Science and Technology

, Volume 22, Issue 5, pp 761–769

Accelerated Parallel Texture Optimization

Regular Paper

DOI: 10.1007/s11390-007-9083-x

Cite this article as:
Huang, HD., Tong, X. & Wang, WC. J Comput Sci Technol (2007) 22: 761. doi:10.1007/s11390-007-9083-x

Abstract

Texture optimization is a texture synthesis method that can efficiently reproduce various features of exemplar textures. However, its slow synthesis speed limits its usage in many interactive or real time applications. In this paper, we propose a parallel texture optimization algorithm to run on GPUs. In our algorithm, k-coherence search and principle component analysis (PCA) are used for hardware acceleration, and two acceleration techniques are further developed to speed up our GPU-based texture optimization. With a reasonable precomputation cost, the online synthesis speed of our algorithm is 4000+ times faster than that of the original texture optimization algorithm and thus our algorithm is capable of interactive applications. The advantages of the new scheme are demonstrated by applying it to interactive editing of flow-guided synthesis.

Keywords

texture synthesis energy minimization parallel GPU flow visualization 

Supplementary material

11390_2007_9083_MOESM1_ESM.pdf (82 kb)
Supplementary material - Chinese Abstract (PDF 81.5 Kb).

Copyright information

© Science Press, Beijing, China and Springer Science + Business Media, LLC, USA 2007

Authors and Affiliations

  1. 1.State Key Lab of Computer Science, Institute of SoftwareChinese Academy of SciencesBeijingChina
  2. 2.Microsoft Research AsiaBeijingChina
  3. 3.Graduate University of Chinese Academy of SciencesBeijingChina