Computing optical flow is a fundamental problem in computer vision. However, deep learning-based optical flow techniques do not perform well for non-rigid movements such as those found in faces, primarily due to lack of the training data representing the fine facial motion. We hypothesize that learning optical flow on face motion data will improve the quality of predicted flow on faces. The aim of this work is threefold: (1) exploring self-supervised techniques to generate optical flow ground truth for face images; (2) computing baseline results on the effects of using face data to train Convolutional Neural Networks (CNN) for predicting optical flow; and (3) using the learned optical flow in micro-expression recognition to demonstrate its effectiveness. We generate optical flow ground truth using facial key-points in the BP4D-Spontaneous dataset. The generated optical flow is used to train the FlowNetS architecture to test its performance on the generated dataset. The performance of FlowNetS trained on face images surpassed that of other optical flow CNN architectures, demonstrating its usefulness. Our optical flow features are further compared with other methods using the STSTNet micro-expression classifier, and the results indicate that the optical flow obtained using this work has promising applications in facial expression analysis.

中文翻译：

---

基于面部运动的光流自监督方法

计算光流是计算机视觉中的基本问题。然而，基于深度学习的光流技术在诸如面部中发现的非刚性运动方面表现不佳，这主要是由于缺乏表示精细面部运动的训练数据所致。我们假设学习面部运动数据上的光流将提高面部预测流的质量。这项工作的目的是三方面的：（1）探索自我监督技术以生成人脸图像的光流地面真相；（2）计算基线结果对使用面部数据训练卷积神经网络（CNN）预测光流的影响；（3）在微表情识别中使用学习到的光流来证明其有效性。我们使用BP4D自发数据集中的面部关键点生成光流地面真相。生成的光流用于训练FlowNetS架构，以测试其在生成的数据集上的性能。在面部图像上训练的FlowNetS的性能超过了其他光流CNN架构，证明了其有用性。我们的光流特征与使用STSTNet微表达分类器的其他方法进行了进一步比较，结果表明，使用这项工作获得的光流在面部表情分析中具有广阔的应用前景。