Skip to main content

🏢 Valeo.ai

ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
·2484 words·12 mins· loading · loading
Computer Vision 3D Vision 🏢 Valeo.ai
ManiPose: Manifold-constrained multi-hypothesis model solves 3D human pose estimation’s depth ambiguity, outperforming state-of-the-art models in pose consistency.