AI Paper Atlas

Research map / 3D vision / Human pose estimation

Towards Viewpoint Invariant 3D Human Pose Estimation

Albert Haque, Boya Peng, Zelun Luo, Alexandre Alahi, Serena Yeung, Li Fei-Fei

ECCV 2016 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 171 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 LSTM recurrent connections to iterative error feedback (ablation)Iterative feedback · ITOP top-view, Upper BodymAP at 10 cm: 51.7 -> 91.4Improved
add LSTM recurrent connections to iterative error feedback (ablation)Iterative feedback · ITOP front-view, Upper BodymAP at 10 cm: 61.0 -> 84.0Improved
add LSTM recurrent connections to iterative error feedback (ablation)Iterative feedback · ITOP front-view, Full BodymAP at 10 cm: 71.0 -> 77.4Improved
add LSTM recurrent connections to iterative error feedback (ablation)Iterative feedback · ITOP top-view, Full BodymAP at 10 cm: 51.2 -> 75.5Improved
add iterative error feedback instead of direct single-pass regression (ablation)Direct prediction · ITOP front-view, Full BodymAP at 10 cm: 21.8 -> 71.0Improved
add iterative error feedback instead of direct single-pass regression (ablation)Direct prediction · ITOP top-view, Upper BodymAP at 10 cm: 17.8 -> 51.7Improved
use glimpse inputs instead of heatmap (indicator mask) inputs (ablation)Recurrent error feedback · ITOP localization error vs iterationsLocalization errorImproved
use learned viewpoint-invariant model instead of random tree walk on frontal-to-top transferRandom tree walk · ITOP viewpoint transfer, Full BodymAP at 10 cm: 2.0 -> 20.4Improved
use recurrent error feedback instead of random tree walk on front view full bodyRandom tree walk · ITOP front-view, Full BodymAP at 10 cm: 80.5 -> 77.4Hurt
use recurrent error feedback instead of random tree walk on top view upper bodyRandom tree walk · ITOP top-view, Upper BodymAP at 10 cm: 84.8 -> 91.4Improved
use deep model instead of random tree walk regarding runtimeRandom tree walk · Runtime per frameseconds per frame: 0.1 -> 1.7Hurt

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