Meta Reality Labs has recently launched an AI model called 'Sapiens,' which has made significant breakthroughs in handling human visual tasks. This model is specifically designed to analyze and understand people and their actions in images or videos, demonstrating outstanding performance in complex environments after rigorous training on over 300 million human images. The core functions of Sapiens include 2D pose estimation, body part segmentation, depth estimation, and surface normal prediction, enabling it to accurately identify human poses, differentiate body parts, and predict...
