arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.09960cs.CV
收藏

快速、准确、稳定的3D密集人脸对齐

Towards Fast, Accurate and Stable 3D Dense Face Alignment

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Beihang University(北京航空航天大学);Westlake University(西湖大学)

Jianzhu Guo, Xiangyu Zhu, Yang Yang, Fan Yang, Zhen Lei, Stan Z. Li

摘要:

现有的三维密集人脸对齐方法主要集中在精度上,限制了其实际应用范围。在本文中,我们提出了一种新的回归框架命名为3DDFA-V2,它使得速度,准确性和稳定性之间的平衡。首先,在轻量级骨干网的基础上,我们提出了一种元联合优化策略,动态回归一组小的3DMM参数,这大大提高了速度和准确性的同时。为了进一步提高视频的稳定性,我们提出了一种虚拟合成的方法,将一个静止的图像转换成一个短视频,其中包括面内和面外的人脸移动。在高精度和稳定性的前提下,3DDFA-V2在单个CPU核心上运行超过50 fps,同时优于其他最先进的重型型号。在几个具有挑战性的数据集上的实验验证了我们的方法的有效性。预先训练的模型和代码可在https://github.com/cleardusk/3DDFA_V2上获得。

英文摘要:

Existing methods of 3D dense face alignment mainly concentrate on accuracy, thus limiting the scope of their practical applications. In this paper, we propose a novel regression framework named 3DDFA-V2 which makes a balance among speed, accuracy and stability. Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously. To further improve the stability on videos, we present a virtual synthesis method to transform one still image to a short-video which incorporates in-plane and out-of-plane face moving. On the premise of high accuracy and stability, 3DDFA-V2 runs at over 50fps on a single CPU core and outperforms other state-of-the-art heavy models simultaneously. Experiments on several challenging datasets validate the efficiency of our method. Pre-trained models and code are available at https://github.com/cleardusk/3DDFA_V2.

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。

↑