atlas

Research map / 3D vision / Human pose estimation

Expressive Body Capture: 3D Hands, Face, and Body From a Single Image

CVPR 2019 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 1,796 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
Use a unified body, hand, and face model rather than SMPL+HSMPL-X fitted with SMPLify-X · EHFv2v error (mm): 54.2 -> 52.9Helped
Use a unified body, hand, and face model rather than body-only SMPLSMPL-X fitted with SMPLify-X · EHFv2v error (mm): 57.6 -> 52.9Helped
Feed Body+Hands+Face keypoints to body-only SMPLSMPL · EHFv2v error (mm): 57.6 -> 64.5Hurt
Use the gender-neutral model instead of a gender-specific model (ablation)SMPLify-X · EHFv2v error (mm): 52.9 -> 58.0Hurt
Add VPoser instead of using the SMPLify GMM pose prior (ablation)SMPLify-X · EHFv2v error (mm): 56.4 -> 52.9Helped
Add the collision term (ablation)SMPLify-X · EHFv2v error (mm): 53.5 -> 52.9Helped
Use SMPL-X rather than the hands-only methodSMPL-X and Panteleris et al. · EHF hand joints3D joint error (mm): 26.5 -> 19.8Helped

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