atlas

Research map / 3D vision / Human pose estimation

End-to-End Recovery of Human Shape and Pose

CVPR 2018 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 1,958 citations (OpenAlex)

Read the paperCheck 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 paired 2D-to-3D supervision during training (ablation)HMR · Human3.6M Protocol 2Reconstruction error (mm): 66.5 -> 56.8Helped
add paired 2D-to-3D supervision during training (ablation)HMR · Human3.6M Protocol 1MPJPE (mm): 106.84 -> 87.97Helped
add paired 2D-to-3D supervision during training (ablation)HMR · MPI-INF-3DHP testMPJPE (mm): 169.5 -> 124.2Helped
add paired 2D-to-3D supervision during training (ablation)HMR · LSP testPart segmentation F1: 0.59 -> 0.60Helped
remove the adversarial prior (ablation)HMR trained without paired 3D supervision · Single-image human mesh reconstructionBody plausibilityHurt
factorize the adversarial prior across shape, individual joint rotations, and whole-body poseHMR · Human mesh reconstructionBody plausibilityHelped

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