AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses
This addresses the problem of accurate facial landmark detection in unconstrained scenarios with large poses for applications in computer vision and face analysis, representing a strong incremental improvement.
The paper tackles facial landmark localization across large pose variations by proposing AnchorFace, a split-and-aggregate strategy using anchor templates for regression, achieving state-of-the-art results on benchmarks like AFLW, 300W, Menpo, and WFLW with efficient inference speed.
Facial landmark localization aims to detect the predefined points of human faces, and the topic has been rapidly improved with the recent development of neural network based methods. However, it remains a challenging task when dealing with faces in unconstrained scenarios, especially with large pose variations. In this paper, we target the problem of facial landmark localization across large poses and address this task based on a split-and-aggregate strategy. To split the search space, we propose a set of anchor templates as references for regression, which well addresses the large variations of face poses. Based on the prediction of each anchor template, we propose to aggregate the results, which can reduce the landmark uncertainty due to the large poses. Overall, our proposed approach, named AnchorFace, obtains state-of-the-art results with extremely efficient inference speed on four challenging benchmarks, i.e. AFLW, 300W, Menpo, and WFLW dataset. Code will be available at https://github.com/nothingelse92/AnchorFace.