AI Paper Atlas

Research map / 3D vision / Human pose estimation

Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data

Shichao Li, Lei Ke, Kevin Pratama, Yu-Wing Tai, Chi-Keung Tang, Kwang-Ting Cheng

CVPR 2020 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 174 citations (OpenAlex)

Check 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
Evolve the S1 training poses and train TAG-Net on the augmented pairs (ablation)2D-to-3D pose estimation · Human3.6M, P1MPJPE: 71.5 -> 60.8Improved
Add cascade to the baseline (ablation)2D-to-3D pose estimation with S1 · Human3.6M, P1MPJPE: 71.5 -> 70.1Improved
Add data evolution to the cascaded model (ablation)2D-to-3D pose estimation with S1 · Human3.6M, P1*MPJPE: 64.5 -> 50.5Improved
Add cascade to the baseline (ablation)2D-to-3D pose estimation with S15678 · Human3.6M, P1MPJPE: 54.3 -> 52.1Improved
Add data evolution to the cascaded model (ablation)2D-to-3D pose estimation with S15678 · Human3.6M, P1*MPJPE: 42.9 -> 34.5Improved
Add heat-map up-sampling (ablation)HRN 2D key-point detector · Human3.6M test2D key-point localization error (pixels): 4.98 -> 4.64Improved
Add soft-argmax (ablation)HRN with heat-map up-sampling · Human3.6M test2D key-point localization error (pixels): 4.64 -> 4.36Improved
Add mutation alongside crossover during data evolution (ablation)Evolved pose training data · Human3.6M, P1*MPJPEImproved
Concatenate current pose estimates to later cascade inputs (ablation)Cascaded 2D-to-3D model · Human3.6MMPJPENo clear effect
Evolve the H36M training distribution and train on 8 million 2D-3D pairs2D-to-3D pose estimation · MPI-INF-3DHP, cross-datasetAUC: 40.8 -> 46.1Improved
Evolve the H36M training distribution and train on 8 million 2D-3D pairs2D-to-3D pose estimation · MPI-INF-3DHP, cross-datasetMPJPE: 117.6 -> 99.7Improved
Use TAG-Net with evolved S15678 data rather than the strongest reported baselineSingle-image 3D pose estimation · Human3.6M, S15678, P1MPJPE: 54.4 -> 50.9Improved

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