SOURCE-LINKED INTELLIGENCE

MEOM: Multi-View Expected-OKS Maximization for Human Pose Triangulation

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Conventional algebraic triangulation solves 3D human pose estimation (HPE) from multi-view 2D keypoints. The typical approach, decoding 2D keypoints from predicted heatmaps, is unreliable as heatmaps can be multimodal under occlusion, and collapsing them into single peaks discards their spatial distribution. We seek to use the entire heatmap to estimate 3D poses more accurately, which requires solving two problems: how to robustly fuse heatmaps across views, and how to assess the reliability of heatmaps. For the former, we introduce a novel objective, Multi-viewExpected-OKS Maximization (MEOM)

Read original source ↗ Open in workspace

recordType

paper

region

Global