Transfer Learning for Pose Estimation of Illustrated Characters
This work addresses the lack of pose estimation tools for illustrated characters, benefiting assistive content creation tasks like animation and retrieval.
The paper tackled pose estimation for illustrated characters by transfer-learning from domain-specific and task-specific source models, achieving state-of-the-art performance and applying it to pose-guided illustration retrieval.
Human pose information is a critical component in many downstream image processing tasks, such as activity recognition and motion tracking. Likewise, a pose estimator for the illustrated character domain would provide a valuable prior for assistive content creation tasks, such as reference pose retrieval and automatic character animation. But while modern data-driven techniques have substantially improved pose estimation performance on natural images, little work has been done for illustrations. In our work, we bridge this domain gap by efficiently transfer-learning from both domain-specific and task-specific source models. Additionally, we upgrade and expand an existing illustrated pose estimation dataset, and introduce two new datasets for classification and segmentation subtasks. We then apply the resultant state-of-the-art character pose estimator to solve the novel task of pose-guided illustration retrieval. All data, models, and code will be made publicly available.