AI Paper Atlas

Research map / 3D vision / Human pose estimation

Probabilistic Monocular 3D Human Pose Estimation With Normalizing Flows

Tom Wehrbein, Marco Rudolph, Bodo Rosenhahn, Bastian Wandt

ICCV 2021 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 144 citations (OpenAlex)

Read the paperCheck 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
add heatmap condition (ablation)normalizing flow pose model · H36MACPS: 137.6 -> 171.0Improved
add L_HM (ablation)normalizing flow pose model · H36MACPS: 157.3 -> 171.0Improved
add discriminator loss L_gen (ablation)normalizing flow pose model · H36MACPS: 165.5 -> 171.0Improved
add discriminator loss L_gen (ablation)normalizing flow pose model · Human3.6M Protocol 2 worst hypothesisPMPJPE (mm): 284.1 -> 86.8Improved
add L_MB multi-best loss (ablation)normalizing flow pose model · H36MAMPJPE: 76.0 -> 71.0Improved
use k=5 in L_MB instead of k=1 (best-of-M) (ablation)normalizing flow pose model · H36MACPS: 167.4 -> 171.0Improved
use k=5 in L_MB instead of k=10 (ablation)normalizing flow pose model · H36MACPS: 168.3 -> 171.0Improved
use k=5 in L_MB instead of k=50 (ablation)normalizing flow pose model · H36MACPS: 168.0 -> 171.0Improved
increase hypotheses from M=1 (z0) to M=200normalizing flow pose model · Human3.6M Protocol 1MPJPE (mm): 61.8 -> 44.3Improved
sample 200 hypotheses instead of 5Li et al. baseline sampled · Human3.6M Protocol 1MPJPE (mm): 74.9 -> 59.6Improved
use flow posterior sampling instead of noise-on-Gaussian baselinenormalizing flow pose model · H36MA increasing samplesMPJPEImproved
use K-Means over 200 hypotheses with 5 clustersnormalizing flow pose model · Human3.6M Protocol 2PMPJPE (mm): 42.6 -> 38.4Improved

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