AI Paper Atlas

Research map / 3D vision / Human pose estimation

DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare

Yuanlu Xu, Song-Chun Zhu, Tony Tung

ICCV 2019 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 187 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 dense render-and-compare losses (ablation)DenseRaC · H3.6M Protocol #1MPJPE: 82.4 -> 79.5Improved
add synthetic data and own body model after render-and-compare (ablation)DenseRaC · H3.6M Protocol #1MPJPE: 79.5 -> 76.8Improved
add dense render-and-compare losses (ablation)DenseRaC · H3.6M Protocol #2MPJPE: 53.9 -> 51.4Improved
add synthetic data and own body model (ablation)DenseRaC · H3.6M Protocol #2MPJPE: 51.4 -> 48.0Improved
add dense render-and-compare losses (ablation)DenseRaC · MPI-INF-3DHP Protocol #1MPJPE: 123.1 -> 124.9Mixed
add synthetic data and own body model (ablation)DenseRaC · MPI-INF-3DHP Protocol #1MPJPE: 124.9 -> 114.2Improved
add adversarial loss (ablation)DenseRaC · MOCA reconstructionMPJPE: 133.0 -> 131.5Improved
add mask loss (ablation)DenseRaC · MOCA reconstructionMPJPE: 131.5 -> 122.8Improved
use dense L_rpj instead of 14-joint-only reprojection (ablation)DenseRaC · MOCA reconstructionMPJPE: 122.8 -> 107.9Improved
add 3D reconstruction loss (ablation)DenseRaC · MOCA reconstructionMPJPE: 122.8 -> 86.5Improved
add regression loss and drop adversarial loss (ablation)DenseRaC · MOCA reconstructionMPJPE: 82.4 -> 80.4Improved
add all loss terms (full model) (ablation)DenseRaC · MOCA reconstructionMPJPE: 80.4 -> 80.3Improved

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