%0 Journal Article
%T Accelerated Parallel Texture Optimization<br>Accelerated parallel texture optimization
%A Hao-Da Huang
%A Xin Tong
%A Wen-Cheng Wang
%A <br>Hao-Da Huang
%A Xin Tong
%A and Wen-Cheng Wang
%J 计算机科学技术学报
%D 2007
%I 
%X Texture optimization is a texture synthesis method that can efficiently reproduce various features of ex- emplar 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 synthe- sis 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.
%K texture synthesis
%K energy minimization
%K parallel
%K GPU
%K flow visualization<br>纹理合成
%K 能量最小化
%K 流程可视化
%K 优化
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=F57FEF5FAEE544283F43708D560ABF1B&aid=CBCDFFE5AEBDB1BFF4D9CAE6F87B9C15&yid=A732AF04DDA03BB3&vid=BC12EA701C895178&iid=94C357A881DFC066&sid=A67EE05E56DA7F45&eid=CA122BD5B2FF2137&journal_id=1000-9000&journal_name=计算机科学技术学报&referenced_num=0&reference_num=19