AI Paper Atlas

Research map / 3D vision / Human pose estimation

Coherent Reconstruction of Multiple Humans From a Single Image

CVPR 2020 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 181 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 interpenetration and depth ordering-aware lossesTop-down SMPL regression (Ours baseline) · Panoptic MeanMean per joint position error: 149.8 -> 143.2Helped
Add interpenetration and depth ordering-aware lossesTop-down SMPL regression (Ours baseline) · MuPoTS-3D All3DPCK: 66.95 -> 69.12Helped
Add interpenetration and depth ordering-aware lossesTop-down SMPL regression (Ours baseline) · MuPoTS-3D Matched3DPCK: 68.96 -> 72.22Helped
Add the interpenetration loss (ablation)Top-down SMPL regression · MuPoTS-3DNumber of collisions: 114 -> 34Helped
Add the interpenetration loss (ablation)Top-down SMPL regression · PoseTrackNumber of collisions: 653 -> 202Helped
Add the depth ordering-aware loss (ablation)Top-down SMPL regression · MuPoTS-3DOrdinal depth relation accuracy: 92.17% -> 93.68%Helped

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