AI Paper Atlas

Research map / 3D vision / Human pose estimation

Probabilistic Modeling for Human Mesh Recovery

Nikos Kolotouros, Georgios Pavlakos, Dinesh Jayaraman, Kostas Daniilidis

ICCV 2021 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 176 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 explicit supervision of the distribution mode (L_mode) (ablation)ProHMR · 3DPWPA-MPJPE: 67.4 -> 59.8Improved
add explicit supervision of the distribution mode (L_mode) (ablation)ProHMR · Human3.6MPA-MPJPE: 54.8 -> 41.2Improved
add explicit supervision of the distribution mode (L_mode) (ablation)ProHMR · MPI-INF-3DHPPA-MPJPE: 76.5 -> 65.0Improved
add image-conditioned prior fitting on top of ProHMR regressionProHMR · 3DPWPA-MPJPE: 59.8 -> 55.1Improved
add image-conditioned prior fitting on top of ProHMR regressionProHMR · Human3.6M GT keypointsPA-MPJPE: 41.2 -> 34.8Improved
add SMPLify fitting (VPoser) on top of SPINSPIN · 3DPWPA-MPJPE: 59.2 -> 70.9Hurt
add EFT fitting on top of SPINSPIN · 3DPWPA-MPJPE: 59.2 -> 56.6Improved
add multi-view fitting with ProHMR prior instead of single-view predictionProHMR · Human3.6M multi-viewPA-MPJPE: 43.7 -> 34.5Improved
use fitting-based multi-view refinement instead of rotation averagingProHMR · Mannequin ChallengePA-MPJPE: 85.1 -> 83.9Improved
use normalizing flow instead of Mixture Density Network for the distributionProHMR · 3DPW multiple hypotheses (n=5)PA-MPJPE: 61.2 -> 56.5Improved
use ProHMR instead of Conditional VAE for the distributionProHMR · Human3.6M multiple hypotheses (n=25)PA-MPJPE: 46.2 -> 36.8Improved
use ProHMR mode instead of SPIN regressionProHMR · MPI-INF-3DHPPA-MPJPE: 67.5 -> 65.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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