Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion Capture
Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion Capture
复制标题
DOI：
10.1109/3dv.2018.00061
复制
发表时间：
2018-08
期刊：
影响因子：
--
通讯作者：
Denis Tomè;M. Toso;L. Agapito;Chris Russell
中科院分区：
文献类型：
--
作者：
Denis Tomè;M. Toso;L. Agapito;Chris Russell
提出了一种基于CNN的多摄像机无标记人体运动捕捉方法。与现有的方法，首先对单个相机进行姿态估计，并生成3D模型作为后处理不同，我们的方法在整个多阶段的方法中使用3D推理。这种新奇使我们能够使用人体姿势的临时3D模型来重新考虑关节应该位于图像中的位置，并从过去的错误中恢复过来。我们对3D人体姿势的原则性改进使我们能够利用图像线索，即使是来自我们以前错误检测关节的图像，也可以作为端到端方法的一部分来改进我们的估计。最后，我们演示了如何将多相机设置的高质量输出用作额外的训练源，以提高现有单相机模型的准确性。
We propose a CNN-based approach for multi-camera markerless motion capture of the human body. Unlike existing methods that first perform pose estimation on individual cameras and generate 3D models as post-processing, our approach makes use of 3D reasoning throughout a multi-stage approach. This novelty allows us to use provisional 3D models of human pose to rethink where the joints should be located in the image and to recover from past mistakes. Our principled refinement of 3D human poses lets us make use of image cues, even from images where we previously misdetected joints, to refine our estimates as part of an end-to-end approach. Finally, we demonstrate how the high-quality output of our multi-camera setup can be used as an additional training source to improve the accuracy of existing single camera models.