Human pose estimation in images is challenging and important for many computer vision applications. Large improvements have been achieved with the development of convolutional neural networks. However, when encountered some difficult cases, even the state-of-the-art models may still fail to predict all the body joints correctly. Some recent works try to refine the pose estimator. GAN (Generative Adversarial Networks) has been proved to be efficient to learn local body joints structural constrains. In this paper, we propose to apply Self-Attention GAN to further improve the performance of human pose estimation. With attention mechanism in the discriminator, we can learn long-range body joints dependencies, therefore enforce the entire body joints structural constrains to make all the body joints to be consistent. Experiments on two standard benchmarks demonstrate the effectiveness of our method.
展开▼
