A Light-Weighted Network for Facial Landmark Detection via Combined Heatmap and Coordinate Regression

Zhengning Wang, Longfei Feng, Fanwei Zeng, Guang Hu, Xiang Zhang, Xia Lv, Fengjun Zhang

Abstract: 3D facial landmark, which offers more expressive and occlusive information than its 2D counterpart, receives more and more attention from researchers in recent years. The top performing algorithms for 3D facial landmark detection are mainly divided into two categories: the two-step approach and the volume representation method. However, the former lacks the relation of depth with plat and the latter leads to large computation. In this paper, we propose the Combined Heatmap and Coordinate Regression (CHCR), which is an end-to-end method for 3D facial landmark detection from a single 2D image. To achieve that, we innovatively present the combined heatmap of three channels, and each channel of heatmap records the likelihoods of landmarks location of any two different axes. Such representation maintains the relation of various view while decreases either the channels for encoding or dimension for decoding. Then we retrieve the 3D coordinate vectors from corresponding combined heatmap by coordinate regression. Hence, an encoder-decoder network with a simple CNN attached to an hourglass module is designed to cope with the whole process. Experiments show our model is extremely light-weighted and runs faster than any other methods while on high performance of accuracy.