AI Paper Atlas

Research map / 3D vision / Human pose estimation

3D Human Pose Estimation via Explicit Compositional Depth Maps

Haiping Wu, Bin Xiao

AAAI 2020 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 29 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
use Limb Depth Maps instead of Joint Depth Maps as depth target (ablation)ResNet-50 pipeline · Human3.6MMPJPE (Z): 37.9 -> 36.3Improved
use Limb Depth Maps instead of Joint Depth Maps as depth target (ablation)ResNet-50 pipeline · Human3.6MP-MPJPE: 41.0 -> 39.3Improved
add 2D heatmap supervision to direct regression (ablation)ResNet-50 pipeline · Human3.6MMPJPE (X,Y): 30.1 -> 27.7Improved
add 2D heatmap supervision to direct regression (ablation)ResNet-50 pipeline · Human3.6MMPJPE (Z): 37.5 -> 37.9Hurt
add limb depth maps on top of 2D heatmaps (explicit depth for lifting) (ablation)ResNet-50 pipeline · Human3.6MMPJPE: 51.7 -> 48.8Improved
add 2D heatmaps and limb depth maps to direct regression (ablation)ResNet-50 pipeline · Human3.6MMPJPE: 52.9 -> 48.8Improved
replace single-frame state of the art with HRNet-W32 version of method (ablation)Ours · Human3.6MMPJPE: 47.3 -> 43.2Improved
compare to 243-frame temporal method using a single frameOurs (HRNet-W32) · Human3.6MMPJPE: 46.8 -> 43.2Mixed

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