Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation
This work addresses the problem of accurate 3D human pose estimation for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles 3D human pose estimation from monocular images by proposing a deep network that learns a joint image-pose embedding using a maximum-margin cost function, achieving state-of-the-art results on the Human3.6m dataset.
This paper focuses on structured-output learning using deep neural networks for 3D human pose estimation from monocular images. Our network takes an image and 3D pose as inputs and outputs a score value, which is high when the image-pose pair matches and low otherwise. The network structure consists of a convolutional neural network for image feature extraction, followed by two sub-networks for transforming the image features and pose into a joint embedding. The score function is then the dot-product between the image and pose embeddings. The image-pose embedding and score function are jointly trained using a maximum-margin cost function. Our proposed framework can be interpreted as a special form of structured support vector machines where the joint feature space is discriminatively learned using deep neural networks. We test our framework on the Human3.6m dataset and obtain state-of-the-art results compared to other recent methods. Finally, we present visualizations of the image-pose embedding space, demonstrating the network has learned a high-level embedding of body-orientation and pose-configuration.