Meta’s Sapiens: Revolutionizing Human Pose, Segmentation, and Depth Estimation with Vision Transformers

In a new paper Sapiens: Foundation for Human Vision Models, a Meta research team introduces Sapiens, a suite of models designed to address four core human-centric vision tasks: 2D pose estimation, ...

By · · 1 min read

Source: syncedreview.com

In a new paper Sapiens: Foundation for Human Vision Models, a Meta research team introduces Sapiens, a suite of models designed to address four core human-centric vision tasks: 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction.