AI Learns Human Pose Estimation From Videos

    DensePose-COCO Dataset We involve human annotators to establish dense correspondences from 2D images to surface-based representations of the human body. If done naively, this would require by manipulating a surface through rotations – which can be frustratingly inefficient. Instead, we construct a two-stage annotation pipeline to efficiently gather annotations for image-to-surface correspondence. As shown below, in the first […]

Continue reading »