Spatial Shortcut Network for Human Pose Estimation
This work improves pose estimation for computer vision applications by reducing computational overhead, though it appears incremental as it builds on existing geometric modeling approaches.
The paper tackles the problem of human pose estimation by addressing the need for spatial information flow without high computational cost, proposing a spatial shortcut network that achieves outstanding performance with a smaller structure.
Like many computer vision problems, human pose estimation is a challenging problem in that recognizing a body part requires not only information from local area but also from areas with large spatial distance. In order to spatially pass information, large convolutional kernels and deep layers have been normally used, introducing high computation cost and large parameter space. Luckily for pose estimation, human body is geometrically structured in images, enabling modeling of spatial dependency. In this paper, we propose a spatial shortcut network for pose estimation task, where information is easier to flow spatially. We evaluate our model with detailed analyses and present its outstanding performance with smaller structure.