Learn Sparse Dictionaries for Edit Propagation
Learn Sparse Dictionaries for Edit Propagation
复制标题
DOI：
10.1109/tip.2016.2523429
复制
发表时间：
2016-04
影响因子：
10.6
通讯作者：
Xiaowu Chen;Jianwei Li;Dongqing Zou;Qinping Zhao
中科院分区：
文献类型：
--
作者：
Xiaowu Chen;Jianwei Li;Dongqing Zou;Qinping Zhao
随着高分辨率图像、视频和3D模型的可用性不断增加，对可扩展的大数据处理技术的需求也在增加。我们介绍了一种稀疏字典学习的方法，用于大输入数据的编辑传播。用于编辑传播的先前方法通常在整个像素（或顶点）集合上采用全局优化，对于大的输入数据导致过高的存储器和时间消耗。我们不是逐像素地传播编辑，而是遵循稀疏表示的原则来获得具有代表性的紧凑字典，并在字典上执行编辑传播。稀疏字典为输入数据提供了一个内在的基础，编码系数捕获了所有像素和字典原子之间的线性关系。然后通过一种新的方案优化学习的字典，该方案最大化每个原子对之间的Kullback-Leibler散度以去除冗余原子。为了实现具有相似外观的图像或视频的局部编辑传播，通过考虑范围约束，提出了一种字典学习策略，以更好地考虑像素在其特征空间中的全局分布。我们展示了基于稀疏性的编辑传播的几个应用程序，包括视频拼接，主题编辑和无缝克隆，在颜色和纹理特征上操作。我们的方法也可以应用于计算机图形任务，如3D表面变形。我们证明，原子与像素比为0.01%左右，这意味着内存消耗显着减少，但我们的方法仍然保持高度的视觉保真度。
With the increasing availability of high-resolution images, videos, and 3D models, the demand for scalable large data processing techniques increases. We introduce a method of sparse dictionary learning for edit propagation of large input data. Previous approaches for edit propagation typically employ a global optimization over the whole set of pixels (or vertexes), incurring a prohibitively high memory and time-consumption for large input data. Rather than propagating an edit pixel by pixel, we follow the principle of sparse representation to obtain a representative and compact dictionary and perform edit propagation on the dictionary instead. The sparse dictionary provides an intrinsic basis for input data, and the coding coefficients capture the linear relationship between all pixels and the dictionary atoms. The learned dictionary is then optimized by a novel scheme, which maximizes the Kullback-Leibler divergence between each atom pair to remove redundant atoms. To enable local edit propagation for images or videos with similar appearance, a dictionary learning strategy is proposed by considering range constraint to better account for the global distribution of pixels in their feature space. We show several applications of the sparsity-based edit propagation, including video recoloring, theme editing, and seamless cloning, operating on both color and texture features. Our approach can also be applied to computer graphics tasks, such as 3D surface deformation. We demonstrate that with an atom-to-pixel ratio in the order of 0.01% signifying a significant reduction on memory consumption, our method still maintains a high degree of visual fidelity.