Zhang Mingjin, Wang Nannan, Li Yunsong, Gao Xinbo
IEEE Trans Neural Netw Learn Syst. 2019 Oct;30(10):3109-3123. doi: 10.1109/TNNLS.2018.2890017. Epub 2019 Jan 22.
Face sketch synthesis is useful and profitable in digital entertainment. Most existing face sketch synthesis methods rely on the assumption that facial photographs/sketches form a low-dimensional manifold. Once the training data are insufficient, the manifold could not characterize the identity-specific information that is included in a test photograph but excluded in the training data. Thus, the synthesized sketch would lose this information, such as glasses, earrings, hairstyles, and hairpins. To provide the sufficient data and satisfy the assumption on manifold, we propose a novel face sketch synthesis framework based on deep latent low-rank representation (DLLRR) in this paper. The DLLRR induces the hidden training sketches with the identity-specific information as the hidden data to the insufficient original training sketches as the observed data. And it searches the lowest rank representation on the candidates of a test photograph from the both hidden and observed data. For the strong representational capability of the coupled autoencoder, we leverage it to reveal the hidden data. Experiment results on face photograph-sketch database illustrate that the proposed method can successfully provide the sufficient training data with the identity-specific information. And compared to the state of the arts, the proposed method synthesizes more clean and vivid face sketches.
面部草图合成在数字娱乐领域既有用又能带来收益。大多数现有的面部草图合成方法都依赖于这样一种假设，即面部照片/草图构成一个低维流形。一旦训练数据不足，该流形就无法表征测试照片中包含但训练数据中排除的身份特定信息。因此，合成的草图会丢失这些信息，比如眼镜、耳环、发型和发夹。为了提供足够的数据并满足关于流形的假设，我们在本文中提出了一种基于深度潜在低秩表示（DLLRR）的新型面部草图合成框架。DLLRR将具有身份特定信息的隐藏训练草图作为隐藏数据引入到不足的原始训练草图中作为观测数据。并且它从隐藏数据和观测数据中在测试照片的候选中搜索最低秩表示。由于耦合自动编码器具有强大的表示能力，我们利用它来揭示隐藏数据。在面部照片 - 草图数据库上的实验结果表明，所提出的方法能够成功地提供具有身份特定信息的足够训练数据。并且与现有技术相比，所提出的方法合成的面部草图更清晰、生动。
