AI Paper Atlas

Research map / 3D vision / Human pose estimation

Deep Feedback Inverse Problem Solver

Wei-Chiu Ma, Shenlong Wang, Jiayuan Gu, Sivabalan Manivasagam, Antonio Torralba, Raquel Urtasun

ECCV 2020 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 15 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 the forward-process feedback signal (compare rendered and observed images) to the regressordeep regression network · 6-DoF pose estimation (ShapeNet silhouettes)mean rotation error (deg): 10.07 -> 2.64Improved
add the forward-process feedback signaldeep regression network · 6-DoF pose estimation (ShapeNet silhouettes)outlier rate (%): 5 -> 2.6Improved
add the feedback signaldeep regression (Janner et al.) · Illumination estimation (directional light)mean error (MSE): 0.067 -> 0.052Improved
add the feedback signaldeep regression (Janner et al.) · Illumination estimation (point light)mean error (MSE): 0.111 -> 0.084Improved
replace differentiable-renderer optimization with the learned feedback updateSoftRas optimization · 6-DoF pose estimation (ShapeNet silhouettes)outlier rate (%): 8.03 -> 2.6Improved
replace differentiable-renderer optimization with the learned feedback updateSoftRas optimization · 6-DoF pose estimation (ShapeNet silhouettes)mean translation error: 0.05 -> 0.02Improved
replace Adam optimization with the learned feedback updateAdam on joint position error · Inverse kinematics (CMU MoCap)mean position error (cm): 0.04 -> 0.64Hurt
replace Adam optimization with the learned feedback updateAdam on joint position error · Inverse kinematics (CMU MoCap)mean rotation error (deg): 7.96 -> 0.88Improved
use rotations farther from the training range at test timeDeep Feedback (Ours) · 6-DoF pose, unseen rotationsmean rotation error (deg): 11.33 -> 24.14Hurt
use the feedback network as initialization for SoftRasSoftRas · 6-DoF pose estimation (ShapeNet silhouettes)error: reduce the error by more than 50%Improved
replace shared update weights with per-step (stage-wise) networks (ablation)Deep Feedback (Ours) · 6-DoF pose estimationerrorImproved
add deep supervision on every intermediate step (ablation)Deep Feedback (Ours) · trainingconvergence speedImproved

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