Facial Landmark Detection With Learnable Connectivity Graph Convolutional Network

The conventional heatmap regression with deep networks has become one of the mainstream approaches for landmark detection. Despite their success, these methods do not exploit the overall landmarks structure. We present a new landmark detection which is capable to capture the overall structure of landmarks by modeling these landmarks as a graph structure. Our method combines a deep heatmap regression network with Graph Convolutional Network (GCN) into an end-to-end differentiable model. The proposed method can utilize both visual information and overall landmarks structure to localize landmarks from an image. The ad hoc spatial relationships between landmarks are learned naturally with GCN network. Experiments on multiple datasets show the robustness of the proposed method.

Automated summary

The conventional heatmap regression with deep networks has achieved success in landmark detection, but fails to fully exploit the overall structure of landmarks. This paper proposes a new landmark detection method that models landmarks as a graph structure, enabling the capture of the overall structure. Experimental results demonstrate the robustness of the proposed method.