AI Paper Atlas

Research map / 3D vision / Human pose estimation

HuMoR: 3D Human Motion Model for Robust Pose Estimation

Davis Rempe, Tolga Birdal, Aaron Hertzmann, Jimei Yang, Srinath Sridhar, Leonidas J. Guibas

ICCV 2021 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 346 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 the learned conditional prior (instead of N(0,I)) (ablation)HuMoR CVAE as test-time prior · i3DB RGB videoglobal joint error all (cm): 95.42 -> 28.15Improved
add the SMPL regularization loss in CVAE training (ablation)HuMoR CVAE as test-time prior · i3DB RGB videoglobal joint error all (cm): 34.33 -> 28.15Improved
add decoder delta prediction (change in state) (ablation)HuMoR CVAE as test-time prior · i3DB RGB videoglobal joint error all (cm): 29.62 -> 28.15Improved
add ground contact classification (ablation)HuMoR CVAE as test-time prior · i3DB RGB videoglobal joint error all (cm): 29.89 -> 28.15Improved
add ground contact classification (ablation)HuMoR CVAE as test-time prior · i3DB RGB videoground penetration frequency: 5.59% -> 2.12%Improved
add decoder delta prediction (ablation)HuMoR CVAE as test-time prior · i3DB RGB videoground penetration distance (cm): 0.58 -> 0.68Hurt
use HuMoR instead of MVAE as the motion priorMVAE prior · AMASS 2s future predictionADE (cm): 25.8 -> 21.5Improved
use HuMoR instead of MVAE as the motion priorMVAE prior · AMASS 3D occluded keypoints fittingpositional error all (cm): 9.52 -> 8.24Improved
use skeleton-consistent rollout (Qual variant) instead of defaultHuMoR · AMASS 2s future predictionFDE (cm): 42.1 -> 46.3Mixed
use HuMoR instead of VPoser-t smoothing prior on noisy jointsVPoser-t · AMASS 3D noisy joints denoisingacceleration (m/s^2): 4.61 -> 5.23Hurt
use HuMoR instead of PROX-RGBPROX-RGB · PROX videos (RGB)ground penetration frequency: 2.55% -> 9.99%Hurt
fit with RGB-D (add point cloud term) instead of RGBHuMoR · PROX videosground penetration frequency: 9.99% -> 5.19%Improved

Later papers that compared with this method

11 later accepted papers report HuMoR as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.

3 more not listed.

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