Fast and Accurate: Structure Coherence Component for Face Alignment
This work addresses the problem of fast and accurate facial landmark localization for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles face alignment by proposing a structure coherence component that uses a dynamic sparse graph to model landmark relations and a Soft Wing loss for improved accuracy, achieving state-of-the-art performance with 0% and 2.88% failure rates on COFW and WFLW datasets.
In this paper, we propose a fast and accurate coordinate regression method for face alignment. Unlike most existing facial landmark regression methods which usually employ fully connected layers to convert feature maps into landmark coordinate, we present a structure coherence component to explicitly take the relation among facial landmarks into account. Due to the geometric structure of human face, structure coherence between different facial parts provides important cues for effectively localizing facial landmarks. However, the dense connection in the fully connected layers overuses such coherence, making the important cues unable to be distinguished from all connections. Instead, our structure coherence component leverages a dynamic sparse graph structure to passing features among the most related landmarks. Furthermore, we propose a novel objective function, named Soft Wing loss, to improve the accuracy. Extensive experiments on three popular benchmarks, including WFLW, COFW and 300W, demonstrate the effectiveness of the proposed method, achieving state-of-the-art performance with fast speed. Our approach is especially robust to challenging cases resulting in impressively low failure rate (0% and 2.88%) in COFW and WFLW datasets.