Hand Image Understanding via Deep Multi-Task Learning
This work addresses the challenge of hand analysis in computer vision for applications like human-computer interaction, but it is incremental as it builds on existing multi-task learning approaches.
The paper tackles the problem of recovering comprehensive hand information from a single RGB image by proposing a Hand Image Understanding (HIU) framework that jointly estimates 2D heat maps, segmentation masks, and 3D information, significantly outperforming state-of-the-art methods on various datasets.
Analyzing and understanding hand information from multimedia materials like images or videos is important for many real world applications and remains active in research community. There are various works focusing on recovering hand information from single image, however, they usually solve a single task, for example, hand mask segmentation, 2D/3D hand pose estimation, or hand mesh reconstruction and perform not well in challenging scenarios. To further improve the performance of these tasks, we propose a novel Hand Image Understanding (HIU) framework to extract comprehensive information of the hand object from a single RGB image, by jointly considering the relationships between these tasks. To achieve this goal, a cascaded multi-task learning (MTL) backbone is designed to estimate the 2D heat maps, to learn the segmentation mask, and to generate the intermediate 3D information encoding, followed by a coarse-to-fine learning paradigm and a self-supervised learning strategy. Qualitative experiments demonstrate that our approach is capable of recovering reasonable mesh representations even in challenging situations. Quantitatively, our method significantly outperforms the state-of-the-art approaches on various widely-used datasets, in terms of diverse evaluation metrics.