AI Paper Atlas

Research map / 3D vision / Human pose estimation

HDNet: Human Depth Estimation for Multi-Person Camera-Space Localization

Jiahao Lin, Gim Hee Lee

ECCV 2020 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 36 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
formulate depth as bin classification with soft-argmax (ablation)HDNet · Human3.6MMRPE_z (mm): 94.5 -> 69.9Improved
formulate depth as bin classification with soft-argmax (ablation)HDNet · MuPoTS-3DAP root @25cm: 27.3 -> 39.4Improved
use separate feature branches for pose and depth (ablation)HDNet · Human3.6MMRPE_z (mm): 72.0 -> 69.9Improved
use separate feature branches for pose and depth (ablation)HDNet · MuPoTS-3DAP root @25cm: 31.9 -> 39.4Improved
add skeleton-based GNN (ablation)HDNet · Human3.6MMRPE_z (mm): 72.9 -> 69.9Improved
add skeleton-based GNN (ablation)HDNet · MuPoTS-3DAP root @25cm: 32.7 -> 39.4Improved
add heatmap attention pooling (ablation)HDNet · Human3.6MMRPE_z (mm): 71.8 -> 69.9Improved
add heatmap attention pooling (ablation)HDNet · MuPoTS-3DAP root @25cm: 26.0 -> 39.4Improved

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