Scribble-based gradient mesh recoloring
Scribble-based gradient mesh recoloring
复制标题
DOI：
10.1007/s11042-017-4987-0
复制
发表时间：
2017-07
影响因子：
3.6
通讯作者：
Liang Wan;Yi Xiao;Ning Dou;Chi-Sing Leung;Yu-Kun Lai
中科院分区：
文献类型：
--
作者：
Liang Wan;Yi Xiao;Ning Dou;Chi-Sing Leung;Yu-Kun Lai
以往的梯度网格优化方法通常依赖于一个附加的参考图像和光栅化的梯度网格。为了避免这种依赖关系，我们提出了一个基于用户涂鸦的标注方法，在该方法中，用户可以用几个颜色的涂鸦来标注梯度网格。我们的方法建立一个辅助网格的梯度网格，即控制网，同时考虑颜色和局部颜色梯度的网格点。然后，我们开发了一个扩展的色度混合方法来传播用户指定的颜色控制网络。最后由重新着色后的控制网重构出重新着色后的梯度网格。实验验证了该方法在多梯度网格上的有效性。与其他方法相比，该方法既没有颜色模糊，也没有采样伪影，并且可以实现快速性能。
Previous gradient mesh recoloring methods usually have dependencies on an additional reference image and the rasterized gradient mesh. To circumvent such dependencies, we propose a user scribble-based recoloring method, in which users are allowed to annotate gradient meshes with a few color scribbles. Our approach builds an auxiliary mesh from gradient meshes, namely control net, by taking both colors and local color gradients at mesh points into account. We then develop an extended chrominance blending method to propagate the user specified colors over the control net. The recolored gradient mesh is finally reconstructed from the recolored control net. Experiments validate the effectiveness of our approach on multiple gradient meshes. Compared with various alternative solutions, our method has no color bleedings nor sampling artifacts, and can achieve fast performance.