期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 34, 期 7, 页码 1437-1444出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2012.77
关键词
Intrinsic images; retinex; nonlocal constraint; texture
资金
- Singapore MOE [R-263-000-555-112, R-263-000-620-112]
- China National Fundamental Research Grant 973 Program [2009CB320802]
We propose a method for intrinsic image decomposition based on retinex theory and texture analysis. While most previous methods approach this problem by analyzing local gradient properties, our technique additionally identifies distant pixels with the same reflectance through texture analysis, and uses these nonlocal reflectance constraints to significantly reduce ambiguity in decomposition. We formulate the decomposition problem as the minimization of a quadratic function which incorporates both the retinex constraint and our nonlocal texture constraint. This optimization can be solved in closed form with the standard conjugate gradient algorithm. Extensive experimentation with comparisons to previous techniques validate our method in terms of both decomposition accuracy and runtime efficiency.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据