AI Paper Atlas

Research map / 3D vision / Human pose estimation

Spatiotemporal Bundle Adjustment for Dynamic 3D Human Reconstruction in the Wild

Minh Vo, Yaser Ajmal Sheikh, Srinivasa G. Narasimhan

TPAMI 2020 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture

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
use motion prior instead of geometric triangulationspatiotemporal BA · CMU Mocap synthetic, dynamic pointsreprojection error: 17.8 -> 0.85Improved
use motion prior instead of generic cubic B-spline trajectory basisspatiotemporal BA · CMU Mocap synthetic, dynamic pointsreprojection error: 1.68 -> 0.85Improved
add DCT resampling to motion prior (incremental) (ablation)spatiotemporal BA · CMU Mocap synthetic, dynamic pointsreprojection error: 0.85 -> 0.74Improved
use divide and conquer instead of incremental reconstructionspatiotemporal BA · CMU Mocap syntheticreprojection error and speed: 0.85 -> 0.89No clear effect
add DCT resampling instead of direct motion prior (ablation)spatiotemporal BA · CMU Mocap syntheticmean 3D error (cm): 6.6 -> 6.5No clear effect
use least action prior instead of least kinetic energy priormotion prior · CMU Mocap time offset estimationoffset biasHurt
use least force prior instead of least kinetic energy prior at low cumulative frame ratemotion prior · CMU Mocap time offset estimationsequencing expressivenessImproved
use least force prior instead of least kinetic at high cumulative frame rate (>=120fps)motion prior · CMU Mocap time offset estimationalignment resultNo clear effect
model rolling shutter readout speed gamma (ablation)spatiotemporal BA · Checkerboard dynamic pointsreprojection error: 1.52 -> 1.21Improved
model rolling shutter readout speed gamma (ablation)spatiotemporal BA · Dance dynamic pointsreprojection error: 2.38 -> 2.13Improved
use motion prior instead of geometric triangulationspatiotemporal BA · Dance real video dynamic pointsRMSE (pixels): 5.23 -> 2.12Improved
add resampling to motion prior (ablation)spatiotemporal BA · real videos dynamic pointsRMSE (pixels): 1.21 -> 1.15Improved

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