atlas

Research map / 3D vision / Human pose estimation

Lifting From the Deep: Convolutional 3D Pose Estimation From a Single Image

CVPR 2017 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 547 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 mixture of PPCA pose models instead of a single PPCA model (ablation)Ours · Human3.6M Protocol #13D error (mm): 92.96 -> 88.39Helped
add 3D pose refinement to the trained CPM architectureCPM · Human3.6M2D pixel error: 10.04 -> 9.47Helped
use the proposed mixture-PPCA method instead of the strongest listed baseline3D pose estimation · Human3.6M Protocol #13D error (mm): 93.15 -> 88.39Helped
use the proposed method instead of Rogez et al.3D pose estimation · Human3.6M Protocol #23D pose error (mm): 88.1 -> 70.7Helped
use the proposed method instead of Bogo et al.3D pose estimation · Human3.6M Protocol #33D pose error (mm): 82.3 -> 79.6Helped

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