Refinement Module based on Parse Graph for Human Pose Estimation
This work addresses efficiency and adaptability issues in human pose estimation, offering a plug-in module that enhances performance incrementally for computer vision researchers and practitioners.
The paper tackles the problem of parameter redundancy and inflexibility in parse graph-based human pose estimation by proposing RMPG, a refinement module that adaptively models hierarchical structure and context relations, resulting in improved accuracy across various architectures with fewer parameters.
Parse graphs have been widely used in Human Pose Estimation (HPE) to model the hierarchical structure and context relations of the human body. However, such methods often suffer from parameter redundancy. More importantly, they rely on predefined network structures, which limits their use in other methods. To address these issues, we propose a new context relation and hierarchical structure modeling module, RMPG (Refinement Module based on Parse Graph). RMPG adaptively refines feature maps through recursive top-down decomposition of feature maps and bottom-up composition of sub-node feature maps with context information. Through recursive hierarchical composition, RMPG fuses local details and global semantics into more structured feature representations, accompanied by context information, thereby improving the accuracy of joint inference. RMPG can be flexibly embedded as a plug-in into various mainstream HPE networks. Moreover, by supervising sub-node features map, RMPG learns the context relations and hierarchical structure between different body parts with fewer parameters. Extensive experiments show that RMPG improves performance across different architectures while effectively modeling hierarchical and context relations of the human body with fewer parameters. The RMPG code can be found at https://github.com/lushbng/RMPG.