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 2003.02953cs.CV
收藏

度量尺度截断鲁棒热图的三维人体姿态估计

Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation

RWTH Aachen University(亚琛工业大学);Robert Bosch GmbH(罗伯特·博世有限公司)

István Sárándi, Timm Linder, Kai O. Arras, Bastian Leibe

摘要:

多年来,热图表示已经形成了2D人体姿态估计系统的基础,但它们对3D姿态的概括只是最近才被考虑。这包括2.5D体积热图,其X和Y轴对应于图像空间,Z轴对应于对象周围的度量深度。为了获得度量尺度的预测,这些方法必须包括一个单独的,明确的后处理步骤,以解决规模的歧义。此外,它们不能对图像边界之外的身体关节位置进行编码,从而在图像截断的情况下导致不完整的姿态估计。我们通过提出度量尺度截断鲁棒(MetTRo)体积热图来解决这些限制,其尺寸在对象附近的度量3D空间中定义,而不是与图像空间对齐。我们训练一个全卷积网络,以端到端的方式从单目RGB估计这样的热图。这种对热图维度的重新解释使我们能够在测试时不了解焦距或人距的情况下估计完整的公制比例姿势,并且在后处理中不依赖人体测量学。此外,由于图像空间与热图空间解耦,网络可以学习推理图像边界以外的关节。使用ResNet-50而不使用任何额外的学习层,我们在Human3.6M和MPI-INF-3DHP基准测试中获得了最先进的结果。由于我们的方法是简单和快速的,它可以成为一个有用的组件,实时自顶向下的多人姿态估计系统。我们公开了我们的代码,以方便进一步的研究(请参阅https://vision.rwth-aachen.de/metro-pose3d)。

英文摘要:

Heatmap representations have formed the basis of 2D human pose estimation systems for many years, but their generalizations for 3D pose have only recently been considered. This includes 2.5D volumetric heatmaps, whose X and Y axes correspond to image space and the Z axis to metric depth around the subject. To obtain metric-scale predictions, these methods must include a separate, explicit post-processing step to resolve scale ambiguity. Further, they cannot encode body joint positions outside of the image boundaries, leading to incomplete pose estimates in case of image truncation. We address these limitations by proposing metric-scale truncation-robust (MeTRo) volumetric heatmaps, whose dimensions are defined in metric 3D space near the subject, instead of being aligned with image space. We train a fully-convolutional network to estimate such heatmaps from monocular RGB in an end-to-end manner. This reinterpretation of the heatmap dimensions allows us to estimate complete metric-scale poses without test-time knowledge of the focal length or person distance and without relying on anthropometric heuristics in post-processing. Furthermore, as the image space is decoupled from the heatmap space, the network can learn to reason about joints beyond the image boundary. Using ResNet-50 without any additional learned layers, we obtain state-of-the-art results on the Human3.6M and MPI-INF-3DHP benchmarks. As our method is simple and fast, it can become a useful component for real-time top-down multi-person pose estimation systems. We make our code publicly available to facilitate further research (see https://vision.rwth-aachen.de/metro-pose3d).

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。

↑