Unsupervised 3D Human Pose Estimation via Conditional Multi-view Ancestral Sampling

Ryohei Goto, Takuya Fujihashi, Shunsuke Saruwatari +1

We propose a method of estimating a 3D human pose from a single view without 3D supervision. The key to our method is to leverage the 2D diffusion priors of motion diffusion models…