AI Paper Atlas

Research map / 3D vision / Human pose estimation

Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation

Helge Rhodin, Mathieu Salzmann, Pascal Fua

ECCV 2018 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 244 citations (OpenAlex)

Read the paper

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
add geometry-aware 3D latent space (ablation)UNet encoder-decoder · Human3.6M S1 (UNet, no rotation aug.)N-MPJPE (mm): 191.7 -> 145.6Improved
add geometry-aware 3D latent space (ablation)UNet encoder-decoder · Human3.6M S1 (UNet, no rotation aug.)P-MPJPE (mm): 139.0 -> 112.2Improved
add separate appearance latent space (ablation)UNet · Human3.6M S1 (UNet, no rotation aug.)N-MPJPE (mm): 159.0 -> 145.6Improved
add separate appearance latent space (ablation)UNet · Human3.6M S1 (UNet, no rotation aug.)P-MPJPE (mm): 117.1 -> 112.2Improved
add separate background handling (ablation)UNet · Human3.6M S1 (UNet, no rotation aug.)N-MPJPE (mm): 159.6 -> 145.6Improved
add separate background handling (ablation)UNet · Human3.6M S1 (UNet, no rotation aug.)P-MPJPE (mm): 124.6 -> 112.2Improved
use deconvolution instead of bilinear upsampling (ablation)UNet · Human3.6M S1 (UNet, no rotation aug.)N-MPJPE (mm): 149.2 -> 145.6Improved
add ResNet-feature (ImageNet) loss (ablation)UNet · Human3.6M S1 (UNet, no rotation aug.)N-MPJPE (mm): 154.1 -> 145.6Improved
use two hidden layers in pose decoder F instead of one (ablation)UNet · Human3.6M S1 (UNet, no rotation aug.)N-MPJPE (mm): 157.4 -> 145.6Improved
use ResNet encoder instead of UNet vs the baseline semi-supervised methodResNet-50 encoder · Human3.6M S1MPJPE: 30.7mm (20 % relative improvement)Improved
use unsupervised geometry-aware representation vs baseline semi-supervised methodUNet · Human3.6M S1MPJPE: 17.4mm (11.3% relative improvement)Improved
use fewer than 180,000 labeled imagesOurs vs baselines · Human3.6MMPJPEMixed

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