人脸画像合成通常是在给定一些训练画像-照片的前提下,将一张输入的人脸照片转换为画像的过程.目前并没有一个系统性的实验对比分析揭示当前此过程面临的挑战以及可能的解决思路.文中对具有代表性的各类方法进行综合深入对比与分析.人脸画像合成方法归纳为2类:数据驱动类方法(即基于样本的方法)和模型驱动类方法.数据驱动方法由3类方法组成:基于子空间学习的方法、基于稀疏表示的方法和基于贝叶斯推断的方法.模型驱动方法直接学习照片到画像的映射关系.文中给出一些之前文献中并未发现的有意义的结论和展望.%Face sketch synthesis refers to generating a sketch from an input face photo with some face sketch-photo pairs as the training set. An experimental study on the existing methods is nontrivial. The comprehensive review and the comparative study on representative face sketch synthesis methods are conducted. These methods are grouped into two categories: data-driven methods, also known as exemplar-based methods, and model-driven methods. Generally, data-driven face sketch synthesis consists of three sub-categories: subspace learning-based methods, sparse representation-based methods and Bayesian inference-based methods. Model-driven methods explicitly learn the mapping from face photos to face sketches. Some previously unknown conclusions are drawn as well.
展开▼
