Gaussian Vector: An Efficient Solution for Facial Landmark Detection
This work solves the problem of efficient and accurate facial landmark detection for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of facial landmark detection by addressing the limitations of existing coordinate regression and heatmap-based methods, which either lose spatial information or have high computational complexity, and proposes Gaussian Vector to preserve spatial information while reducing output size and simplifying post-processing, achieving significant performance improvements on datasets like 300W, COFW, WFLW, and JD-landmark.
Significant progress has been made in facial landmark detection with the development of Convolutional Neural Networks. The widely-used algorithms can be classified into coordinate regression methods and heatmap based methods. However, the former loses spatial information, resulting in poor performance while the latter suffers from large output size or high post-processing complexity. This paper proposes a new solution, Gaussian Vector, to preserve the spatial information as well as reduce the output size and simplify the post-processing. Our method provides novel vector supervision and introduces Band Pooling Module to convert heatmap into a pair of vectors for each landmark. This is a plug-and-play component which is simple and effective. Moreover, Beyond Box Strategy is proposed to handle the landmarks out of the face bounding box. We evaluate our method on 300W, COFW, WFLW and JD-landmark. That the results significantly surpass previous works demonstrates the effectiveness of our approach.