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 1705.03098cs.CV
收藏

一种简单有效的三维人体姿态估计基线

A simple yet effective baseline for 3d human pose estimation

University of British Columbia(不列颠哥伦比亚大学);Body Labs Inc.(Body Labs公司)

Julieta Martinez, Rayat Hossain, Javier Romero, James J. Little

摘要:

在深度卷积网络取得成功之后,用于3d人体姿态估计的最先进方法集中在深度端到端系统上,该系统在给定原始图像像素的情况下预测3d关节位置。尽管它们表现出色,但通常不容易理解它们剩余的错误是否源于有限的2d姿势(视觉)理解,或者未能将2d姿势映射到三维位置。为了理解这些误差来源,我们开始构建一个系统,给定2d关节位置预测3d位置。令我们非常惊讶的是,我们发现,利用当前的技术,“提升”地面真实2D关节位置到3D空间是一项可以以非常低的出错率解决的任务:相对简单的深度前馈网络在Human3.6M上的表现优于最好的报告结果约30%,Human3.6M是最大的公开可用的3D姿态估计基准。此外,在现成的最先进的2D检测器(\ie,使用图像作为输入)的输出上训练我们的系统会产生最先进的结果-这包括专门为此任务进行端到端训练的系统阵列。我们的研究结果表明,现代深度三维姿态估计系统的大部分误差源于他们的视觉分析,并建议进一步推进三维人体姿态估计的最新技术水平的方向。

英文摘要:

Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d pose (visual) understanding, or from a failure to map 2d poses into 3-dimensional positions. With the goal of understanding these sources of error, we set out to build a system that given 2d joint locations predicts 3d positions. Much to our surprise, we have found that, with current technology, "lifting" ground truth 2d joint locations to 3d space is a task that can be solved with a remarkably low error rate: a relatively simple deep feed-forward network outperforms the best reported result by about 30\% on Human3.6M, the largest publicly available 3d pose estimation benchmark. Furthermore, training our system on the output of an off-the-shelf state-of-the-art 2d detector (\ie, using images as input) yields state of the art results -- this includes an array of systems that have been trained end-to-end specifically for this task. Our results indicate that a large portion of the error of modern deep 3d pose estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human pose estimation.

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。

↑