atlas

Research map / 3D vision / Human pose estimation

Unsupervised 3D Pose Estimation With Geometric Self-Supervision

CVPR 2019 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 210 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 geometric self-consistency to the 2D pose discriminator (ablation)3D lifter · Human3.6MMPJPE: 61 -> 58Helped
Use self-consistency alone instead of the 2D pose discriminator (ablation)3D lifter · Human3.6MMPJPE: 61 -> 162Hurt
Add symmetry constraints to self-consistency alone (ablation)3D lifter · Human3.6MMPJPE: 162 -> 168Hurt
Add adapted Kinetics 2D poses (ablation)Adv + SS lifter · Human3.6MMPJPE: 58 -> 55Helped
Add the temporal discriminator during training (ablation)Adv + SS + DA lifter · Human3.6MMPJPE: 55 -> 51Helped
Fine-tune with 5% of Human3.6M 3D data (ablation)Unsupervised model · Human3.6MMPJPE: 55 -> 37Helped
Use 17M completed Kinetics skeletons instead of 9M complete skeletons (ablation)3D lifter · Human3.6MMPJPE: 55 -> 48Helped

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