HumanoidPose: Estimating Full-Body Joint Poses of Humanoid Robots from Video

The paper proposes the HumanoidPose framework, which treats vision as proprioception and recovers a humanoid robot's full-body joint configuration in world coordinates from video alone. The method combines pretrained human pose features with robot kinematics in a unified model and retargets human motions to sixteen different humanoid embodiments, enabling scalable learning entirely from synthetic data; it also uses unlabeled online videos through self-training to develop a 2D robot pose detector to improve real-world generalization.