论文标题
姿势指导人图像合成的强大姿势转化gan
A Robust Pose Transformational GAN for Pose Guided Person Image Synthesis
论文作者
论文摘要
在任何看不见的姿势中生成人类受试者的感性图像对于产生受试者的完整外观模型具有至关重要的应用。但是，从计算机视觉的角度来看，由于无法建模以姿势为条件的数据分布，该任务变得极大地具有挑战性。现有作品使用复杂的姿势转化模型，具有各种其他功能，例如前景分割，人体解析等，以实现鲁棒性，从而导致计算开销。在这项工作中，我们通过使用残差学习方法提出了一个简单而有效的姿势转化gan，而无需任何其他特征学习以在任何任意姿势中产生给定的人类形象。使用有效的数据增强技术并巧妙地调整模型，我们在照明，遮挡，失真和规模方面实现了鲁棒性。我们提出了一项详细的研究，包括定性和定量性，以证明我们的模型优于两个大数据集上的现有方法。
Generating photorealistic images of human subjects in any unseen pose have crucial applications in generating a complete appearance model of the subject. However, from a computer vision perspective, this task becomes significantly challenging due to the inability of modelling the data distribution conditioned on pose. Existing works use a complicated pose transformation model with various additional features such as foreground segmentation, human body parsing etc. to achieve robustness that leads to computational overhead. In this work, we propose a simple yet effective pose transformation GAN by utilizing the Residual Learning method without any additional feature learning to generate a given human image in any arbitrary pose. Using effective data augmentation techniques and cleverly tuning the model, we achieve robustness in terms of illumination, occlusion, distortion and scale. We present a detailed study, both qualitative and quantitative, to demonstrate the superiority of our model over the existing methods on two large datasets.
