ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation Cédric Rommel 1 Victor Letzelter 1,3

We propose ManiPose, a manifold-constrained multi-hypothesis model for humanpose 2D-to-3D lifting. We provide theoretical and empirical evidence that, due to the depth ambiguity inherent to monocular 3D human pose estimation, traditional regression models suffer from pose-topology consistency issues, which standard evaluation metrics (MPJPE, P-MPJPE and PCK) fail to assess. ManiPose addresses depth ambiguity by proposing multiple candidate 3D poses for each 2D input, each with its estimated plausibility.