Integral Human Pose Regression
This work addresses a specific bottleneck in human pose estimation for computer vision applications, offering a novel method that is incremental but enhances existing approaches.
The paper tackled the issues of non-differentiability and quantization error in heat map-based human pose estimation by introducing an integral operation that unifies heat map representation and joint regression, achieving improved performance in 3D pose estimation as validated through comprehensive experiments.
State-of-the-art human pose estimation methods are based on heat map representation. In spite of the good performance, the representation has a few issues in nature, such as not differentiable and quantization error. This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues. It is differentiable, efficient, and compatible with any heat map based methods. Its effectiveness is convincingly validated via comprehensive ablation experiments under various settings, specifically on 3D pose estimation, for the first time.