arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.09501cs.CV
收藏

一种用于稳定人脸对齐的骨干可替换微调框架

A Backbone Replaceable Fine-tuning Framework for Stable Face Alignment

Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学)

Xu Sun, Zhenfeng Fan, Zihao Zhang, Yingjie Guo, Shihong Xia

摘要:

基于热图回归的人脸对齐算法在静态图像上取得了显著的效果。然而,当将现有的方法应用于动态视频时,稳定性和准确性显着打折扣。我们将这种退化归因于视频中常见的随机噪声和运动模糊。时间信息对于解决这一问题至关重要,但在现有工作中尚未充分考虑。在本文中,我们访问面向视频的人脸对齐问题在两个方面:检测精度更倾向于较低的误差为一个单一的帧,检测一致性的力量相邻帧之间的稳定性更好。在此基础上,我们提出了一个抖动损失函数,利用时间信息来抑制不准确以及抖动的地标。抖动损失涉及到一个新的框架,该框架在骨干可替换网络上具有微调的ConvLSTM结构。我们进一步证明了准确和稳定的地标与在规范坐标中具有重叠的不同区域相关联,基于此,所提出的抖动损失促进了训练过程中的优化过程。所提出的框架实现了至少40%的稳定性评估指标的改善,同时提高检测精度与国家的最先进的方法。一般来说,它可以快速地将面部图像的地标检测器转换为性能更好的视频检测器,而无需重新训练整个模型。

英文摘要:

Heatmap regression based face alignment has achieved prominent performance on static images. However, the stability and accuracy are remarkably discounted when applying the existing methods on dynamic videos. We attribute the degradation to random noise and motion blur, which are common in videos. The temporal information is critical to address this issue yet not fully considered in the existing works. In this paper, we visit the video-oriented face alignment problem in two perspectives: detection accuracy prefers lower error for a single frame, and detection consistency forces better stability between adjacent frames. On this basis, we propose a Jitter loss function that leverages temporal information to suppress inaccurate as well as jittered landmarks. The Jitter loss is involved in a novel framework with a fine-tuning ConvLSTM structure over a backbone replaceable network. We further demonstrate that accurate and stable landmarks are associated with different regions with overlaps in a canonical coordinate, based on which the proposed Jitter loss facilitates the optimization process during training. The proposed framework achieves at least 40% improvement on stability evaluation metrics while enhancing detection accuracy versus state-of-the-art methods. Generally, it can swiftly convert a landmark detector for facial images to a better-performing one for videos without retraining the entire model.

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。

↑