论文标题
引导人类的光流和姿势
Bootstrapping Human Optical Flow and Pose
论文作者
论文摘要
我们提出了一个自举框架，以增强人类的光流和姿势。我们表明，对于涉及人类在场景中的视频，我们可以通过同时考虑这两个任务来改善人类的光流和姿势估计质量。我们通过微调拟合人姿势估计来增强光流估计，反之亦然。更详细地，我们优化了姿势和光流网络，以在推理时间相互同意。我们表明，这导致了最新的野生数据集中36m和3D姿势的最新结果，以及Sintel数据集的与人类相关的子集，既取决于姿势估计的准确性和人类关节位置的光学流量准确性。可在https://github.com/ubc-vision/bootstrapping-human-optical-flow-and-pose上找到代码
We propose a bootstrapping framework to enhance human optical flow and pose. We show that, for videos involving humans in scenes, we can improve both the optical flow and the pose estimation quality of humans by considering the two tasks at the same time. We enhance optical flow estimates by fine-tuning them to fit the human pose estimates and vice versa. In more detail, we optimize the pose and optical flow networks to, at inference time, agree with each other. We show that this results in state-of-the-art results on the Human 3.6M and 3D Poses in the Wild datasets, as well as a human-related subset of the Sintel dataset, both in terms of pose estimation accuracy and the optical flow accuracy at human joint locations. Code available at https://github.com/ubc-vision/bootstrapping-human-optical-flow-and-pose
