Deep learning technique has dramatically boosted the performance of face alignment algorithms. However, due to large variability and lack of samples, the alignment problem in unconstrained situations, \emph{e.g}\onedot large head poses, exaggerated expression, and uneven illumination, is still largely unsolved. In this paper, we explore the instincts and reasons behind our two proposals, \emph{i.e}\onedot Propagation Module and Focal Wing Loss, to tackle the problem. Concretely, we present a novel structure-infused face alignment algorithm based on heatmap regression via propagating landmark heatmaps to boundary heatmaps, which provide structure information for further attention map generation. Moreover, we propose a Focal Wing Loss for mining and emphasizing the difficult samples under in-the-wild condition. In addition, we adopt methods like CoordConv and Anti-aliased CNN from other fields that address the shift-variance problem of CNN for face alignment. When implementing extensive experiments on different benchmarks, \emph{i.e}\onedot WFLW, 300W, and COFW, our method outperforms state-of-the-arts by a significant margin. Our proposed approach achieves 4.05\% mean error on WFLW, 2.93\% mean error on 300W full-set, and 3.71\% mean error on COFW.
翻译:深层学习技术极大地提升了面部校正算法的性能。然而,由于巨大的变异性和缺乏样本,在未受限制的情况下,在未受限制的情况下,人们会遇到校正问题,例如:eemph{e{onedot大头的姿势、夸大表情和不均匀的照明,这些问题基本上仍未解决。在本文中,我们探讨了我们两项提案的本能和理由,即:eemph{i_e ⁇ onedoporation 模块和焦点翼损失,以解决问题。具体地说,我们展示了一种新的结构化的面部校正算法,其依据是:通过传播里程碑式的热映射到边界的热映射仪,提供结构信息,供进一步关注地图的生成。此外,我们提议了一个核心木头损失中心,并在电站的状态下强调困难的样品。此外,我们采用了Coord Conv和反反反目标的CNNCN网络方法,以解决轮值波动问题,以面对面的方式。当在不同基准上进行广泛的实验时, emp{onedot-ointW, 300W, 300W, 和CO-fremealfrogres, 我们的拟议在正值的错误上,我们提出的一个重大的错误。