A learning-based approach for automatic image and video colorization
Abstract： 本文作者提出了一个无须人为干预的灰度图上色算法。 算法以 superpixel 为 gt（如此一来就是单通道到单通道的映射），来学习不同图片特征及其相对应的颜色之间的关系。通过学习到的信息来预测灰度图每一个超像素块的 color value。 相较于处理单个的像素点，超像素的做法可以更好的保持空间一致性，并加速整个上色过程。The predicted color values of the gray-scale image superpixels are used to provide a ’micro-scribble’ at the centroid of the superpixels. These color scribbles are refined by using a voting based approach. To generate the final colorization result, we use an optimization-based approach to smoothly spread the color scribble across all pixels within a superpixel. Experimental results on a broad range of images and the comparison with existing state-of-the-art colorization methods demonstrate the greater effectiveness of the proposed algorithm.
Introduction： 仅使用一维信息（亮度或强度 ）将三维信息整合进灰度图的一个像素点上去的过程即为上色。
交互上色由 user 手动提供一些颜色信息，例如manually marked color scribbles or the pre-segmented regions.然后使用optimization based framework 将这些额外信息扩展到整张图。
自动上色是通过对一张或多张彩色图的学习，自动的将颜色 transfer 到灰度图上。
Based on the local appearance of these superpixels and their neighboring superpixels, we compute a set of image features for each of these superpixels. We quantize the average color values of the reference color image superpixels to compute a color label for each of these superpixels. The image features computed for reference image superpixels and their corresponding color labels are then used to train a randomize decision forest.
While transferring the color values corresponding to the color labels, authors transfer only chromaticity（色度） values as a micro-scribble at the centroid of the grayscale image superpixels and then refine these micro-scribbles by using a voting-based approach.