AI Paper Atlas

Research map / 3D vision / Human pose estimation

Consensus-Based Optimization for 3D Human Pose Estimation in Camera Coordinates

Diogo Carbonera Luvizon, David Picard, Hedi Tabia

IJCV 2022 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 34 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add multi-view fusion with ground-truth calibrationmonocular absolute pose network · Human3.6M test setMPJPE average (mm): 52 -> 39Improved
add multi-view consensus optimization with estimated calibrationmonocular absolute pose network · Human3.6M test setMPJPE average (mm): 52 -> 45Improved
use ground-truth instead of estimated calibration for multi-view (ablation)consensus optimization · Human3.6M validationMPJPE (mm): 44.7 -> 36.9Improved
add a third camera view to two views (GT calibration) (ablation)multi-view pose estimation · Human3.6M validationMPJPE (mm): 45.7 -> 41.8Improved
add a fourth camera view to three views (GT calibration) (ablation)multi-view pose estimation · Human3.6M validationMPJPE (mm): 41.8 -> 36.9Improved
add the refinement network (ResNet-U) instead of ResNet cut at block 5 (ablation)pose backbone · Human3.6M validationMPJPE (mm): 53.7 -> 50.5Improved
use backbone cut at block 5 instead of block 4 (ablation)ResNet backbone · Human3.6M validationMPJPE (mm): 62.2 -> 53.7Improved
add CNN visual features to bounding box features for absolute depth (ablation)absolute root depth estimation · Human3.6M validationMRPE (mm): 375.4 -> 80.1Improved
add bounding box position to CNN features for absolute depth (ablation)absolute root depth estimation · Human3.6M validationMRPE (mm): 100.1 -> 80.1Improved
use monocular-trained network on another dataset with different intrinsics (zero-shot, with torso rescaling)absolute pose model · KTHPCP: 0.812 and .929 legs; 0.620 and 0.804 armsMixed
use method against best prior approach on total metricsmonocular model · MPI-INF-3DHPMPJPE total (mm): 112.1 vs 105.2Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy