arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.03132cs.CV
收藏

面向细粒度的面部表情操纵

Toward Fine-grained Facial Expression Manipulation

Shanghai Jiao Tong University(上海交通大学)

Jun Ling, Han Xue, Li Song, Shuhui Yang, Rong Xie, Xiao Gu

摘要:

人脸表情操作的目的是在给定的条件下编辑人脸表情。先前的方法在离散情感标签或绝对条件(例如,面部动作单元)以拥有期望的表情。然而,这些方法要么遭受不断变化的条件无关的区域,或者是低效率的细粒度编辑。在这项研究中,我们考虑到这两个目标,并提出了一种新的方法。首先,我们用相对条件,具体地说,相对动作单位来代替连续的绝对条件。通过相对动作单元,生成器学习仅变换由非零值相对AU指定的感兴趣区域。其次,我们的生成器是建立在U-Net上的,但通过多尺度特征融合(MSF)机制进行了加强,以实现高质量的表达式编辑目的。大量的定量和定性评价实验表明,我们提出的方法相比,国家的最先进的表达编辑方法的改进。代码可在\url{https://github.com/junleen/Expression-manipulator}上获得。

英文摘要:

Facial expression manipulation aims at editing facial expression with a given condition. Previous methods edit an input image under the guidance of a discrete emotion label or absolute condition (e.g., facial action units) to possess the desired expression. However, these methods either suffer from changing condition-irrelevant regions or are inefficient for fine-grained editing. In this study, we take these two objectives into consideration and propose a novel method. First, we replace continuous absolute condition with relative condition, specifically, relative action units. With relative action units, the generator learns to only transform regions of interest which are specified by non-zero-valued relative AUs. Second, our generator is built on U-Net but strengthened by Multi-Scale Feature Fusion (MSF) mechanism for high-quality expression editing purposes. Extensive experiments on both quantitative and qualitative evaluation demonstrate the improvements of our proposed approach compared to the state-of-the-art expression editing methods. Code is available at \url{https://github.com/junleen/Expression-manipulator}.

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。

↑