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 2202.06198cs.CV
收藏

面向鲁棒唇形同步的数据标准化

Data standardization for robust lip sync

Mashang Consumer Finance Co., Ltd.(马尚消费金融有限公司)

Chun Wang

AI总结:

本文提出面向唇形同步的视觉数据标准化流程,通过三维人脸重建解耦唇动并固定干扰属性,从而提升现有方法的数据效率、鲁棒性及主动说话者检测性能。

摘要:

唇形同步是一项基础的音视觉任务。然而,现有唇形同步方法在自然场景中仍缺乏鲁棒性。一个重要原因可能是视觉输入侧存在干扰因素,使唇动信息的提取变得困难。为解决这些问题,本文提出一种数据标准化流程,用于标准化唇形同步的视觉输入。基于三维人脸重建的最新进展,我们首先构建了一个模型,能够从原始图像中一致地解耦出唇动信息。随后,利用解耦得到的唇动信息合成标准化图像,并将与干扰因素相关的所有其他属性设置为独立于输入的预定义值,以降低其影响。使用合成图像后,现有唇形同步方法提升了数据效率和鲁棒性,并在主动说话者检测任务上取得了具有竞争力的性能。

英文摘要:

Lip sync is a fundamental audio-visual task. However, existing lip sync methods fall short of being robust in the wild. One important cause could be distracting factors on the visual input side, making extracting lip motion information difficult. To address these issues, this paper proposes a data standardization pipeline to standardize the visual input for lip sync. Based on recent advances in 3D face reconstruction, we first create a model that can consistently disentangle lip motion information from the raw images. Then, standardized images are synthesized with disentangled lip motion information, with all other attributes related to distracting factors set to predefined values independent of the input, to reduce their effects. Using synthesized images, existing lip sync methods improve their data efficiency and robustness, and they achieve competitive performance for the active speaker detection task.

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。

↑