nx_pose_estimate.nx

nx_pose_estimate.nx -- LEARNED pose localization from an image (roadmap R2 v0, the video->POSE keystone gap). Sovereign + deterministic, the text2motion playbook: a silhouette (z-buffer occupancy grid) -> a PERCEPTRON that classifies WHERE a keypoint is (a coarse region). Trained on rendered rig poses (we generate the data), proven by HELD-OUT generalization. Honest ceiling: coarse region-classification of ONE joint on OUR-render silhouettes; SOTA = precise full-body keypoints from real video via a trained CNN (OpenPose/MoveNet). The architecture (image feature -> learned classifier -> keypoint) is the real thing at small scale. ORIGINAL