"Teaching Independent Parts Separately"(TIPS-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Human Pose Estimation. (arXiv:2205.05980v1 [cs.CV])

We present TIPS-GAN, a new approach to improve the accuracy and stability in
unsupervised adversarial 2D to 3D human pose estimation. In our work we
demonstrate that the human kinematic skeleton should not be assumed as one
spatially dependent structure. In fact, we believe when a full 2D pose is
provided during training, there is an inherent bias learned where the 3D
coordinate of a keypoint is spatially codependent on the 2D locations of all
other keypoints. To investigate our …

3d accuracy arxiv cv gan human independent teaching tips unsupervised