arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.11697cs.CV
收藏

Fast and Accurate:用于人脸对齐的结构一致性组件

Fast and Accurate: Structure Coherence Component for Face Alignment

SenseTime Research(商汤科技研究院);University of Toronto(多伦多大学)

Beier Zhu, Chunze Lin, Quan Wang, Renjie Liao, Chen Qian

摘要:

本文提出了一种快速、准确的人脸配准坐标回归方法。与大多数现有的面部地标回归方法,通常采用完全连接的层,将特征图转换为地标坐标,我们提出了一个结构的连贯性组件,明确考虑到面部地标之间的关系。由于人脸的几何结构,不同面部部位之间的结构一致性为有效定位面部标志提供了重要线索。然而,全连接层中的密集连接过度使用了这种连贯性,使得重要的线索无法从所有连接中区分出来。相反,我们的结构一致性组件利用动态稀疏图结构在最相关的地标之间传递特征。此外,我们提出了一种新的目标函数,命名为软翼损失,以提高精度。在三个流行的基准测试,包括WFLW,COFW和300 W,广泛的实验证明了所提出的方法的有效性,实现了最先进的性能与快速。我们的方法对于具有挑战性的情况特别强大,导致COFW和WFLW数据集的失败率非常低(0%和2.88%)。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑