In facial landmark localization tasks, various occlusions heavily degrade the localization accuracy due to the partial observability of facial features. This paper proposes a structural relation network (SRN) for occlusion-robust landmark localization. Unlike most existing methods that simply exploit the shape constraint, the proposed SRN aims to capture the structural relations among different facial components. These relations can be considered a more powerful shape constraint against occlusion. To achieve this, a hierarchical structural relation module (HSRM) is designed to hierarchically reason the structural relations that represent both long- and short-distance spatial dependencies. Compared with existing network architectures, HSRM can efficiently model the spatial relations by leveraging its geometry-aware network architecture, which reduces the semantic ambiguity caused by occlusion. Moreover, the SRN augments the training data by synthesizing occluded faces. To further extend our SRN for occluded video data, we formulate the occluded face synthesis as a Markov decision process (MDP). Specifically, it plans the movement of the dynamic occlusion based on an accumulated reward associated with the performance degradation of the pre-trained SRN. This procedure augments hard samples for robust facial landmark tracking. Extensive experimental results indicate that the proposed method achieves outstanding performance on occluded and masked faces. Code is available at https://github.com/zhuccly/SRN.
翻译:在面部标志性本地化任务中,由于面部特征部分可视性,各种封闭性大大降低了本地化的准确性。本文件建议为封闭性-机器人标志性本地化建立一个结构关系网络(SRN),以建立结构关系网络(SRN)。与大多数仅利用形状限制的现有方法不同,拟议的SRN旨在捕捉不同面部组成部分之间的结构关系。这些关系可被视为一种对封闭性更强大的形状限制。为此,一个等级结构关系模块(HSRM)旨在从等级上解释代表长距离和短距离空间依赖性的结构关系。与现有网络结构相比,HSRM能够有效地模拟空间关系,利用其地理测量性网络结构来减少空间关系,从而减少隐形性约束造成的语系模糊性。此外,SRNN将扩大培训数据,通过合成隐蔽性视频数据,我们将隐蔽面部面部面部合成作为Markov的决策过程(MDP) 。具体地说,HSRMMM(M)可以有效地模拟空间关系关系,通过利用其地理测量性网络结构结构结构结构结构结构结构结构结构结构结构来减少空间关系,从而减少封闭性网络性网络内隐性网络内隐化的演化结果,以累积性地表化的升级化地分析。根据累积性地表质化的变压化法,以累积性地表质化的演化法,根据累积性地表化的变化法,在累积性地表化法,以累积性地表化法的变化法进行升级化法的演化法的演化的演化法,以累积性化的演化的演化法,以累积性化的演化法化法化法化法化法化法化法化法化法化法化法,以累积性化法化法化法化法化的演化法化法。