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 2402.02736cs.CVcs.LG
收藏

利用运动线索在低数据条件下监督单帧人体姿态与形状估计

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

CVLab, EPFL(洛桑联邦理工学院计算机视觉实验室);Meta AI

Andrey Davydov, Alexey Sidnev, Artsiom Sanakoyeu, Yuhua Chen, Mathieu Salzmann, Pascal Fua

AI总结:

针对标注数据稀缺时单帧人体姿态与形状估计性能下降的问题,提出利用未标注视频的运动线索(光流一致性)作为额外监督信号,有效优化网络权重,达到与充足标注数据训练相当的性能。

摘要:

当有足够的标注训练数据时,监督式深度学习算法能够利用单摄像头出色地估计人体姿态和形状。当此类数据过少时,其影响可通过利用其他信息源(如人体形状数据库)来学习先验知识而得到缓解。然而,此类信息源并非总是可得。我们证明,在这种情况下,易于获取的未标注视频可被用来提供所需的监督信号。给定一个使用过少标注数据训练的模型,我们计算连续帧中的姿态以及它们之间的光流。然后,我们强制图像光流与根据相邻帧间姿态变化推断出的光流保持一致。这提供了足够的额外监督,以有效优化网络权重,并达到与使用更多标注数据训练的方法相当的性能。

英文摘要:

When enough annotated training data is available, supervised deep-learning algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sources, such as databases of body shapes, to learn priors. Unfortunately, such sources are not always available either. We show that, in such cases, easy-to-obtain unannotated videos can be used instead to provide the required supervisory signals. Given a trained model using too little annotated data, we compute poses in consecutive frames along with the optical flow between them. We then enforce consistency between the image optical flow and the one that can be inferred from the change in pose from one frame to the next. This provides enough additional supervision to effectively refine the network weights and to perform on par with methods trained using far more annotated data.

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。

↑