AI Paper Atlas

Research map / 3D vision / Human pose estimation

Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot

Fabien Baradel, Thomas LUCAS, Matthieu Armando, Salma Galaaoui, Romain Brégier, Philippe Weinzaepfel, Gregory Rogez

ECCV 2024 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 71 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
replace HRNet with a ViT backbone (ablation)Multi-HMR with HPH · EHF PVE-AllPVE: 115.2 -> 80.1Improved
replace iterative regressor with the cross-attention Human Perception Head (ablation)Multi-HMR ViT-B · EHF PVE-AllPVE: 65.0 -> 55.3Improved
add self-attention across person queries in HPH (ablation)HPH · EHF PVE-AllPVE: 63.2 -> 55.3Improved
increase HPH layers from 2 to 8 (ablation)HPH · MuPoTs PCK / EHF PVEPCK / PVE: 76.3 -> 78.9 PCK; 55.3 -> 51.0 PVEImproved
train on synthetic data (BEDLAM+AGORA) instead of real data (ablation)Multi-HMR ViT-B · EHF PVE-AllPVE: 70.2 -> 55.3Improved
add CUFFS close-up synthetic dataset (ablation)Multi-HMR ViT-B · EHF-H PVE-HandsPVE: 47.4 -> 40.5Improved
mix real-world data with synthetic data (ablation)Multi-HMR ViT-B · EHF PVE-AllPVE: 49.8 -> 61.1Hurt
increase input resolution (ablation)Multi-HMR · MuPoTs, CMU, EHFaccuracy and speedMixed
embed flattened intrinsics matrix through a linear layer (ablation)Multi-HMR ViT-B · MuPoTs PCKPCK: 76.3 -> 74.8Hurt
add ray-direction camera embedding with focal length normalization (ablation)Multi-HMR ViT-B · MuPoTs PCKPCK: 76.3 -> 78.8Improved
give ground-truth intrinsics at train and test time (ablation)Multi-HMR · MuPoTs MRPEMRPE: 1345 -> 693Improved
use camera intrinsics for reconstruction metrics (ablation)Multi-HMR · MuPoTs/3DPW/CMU reconstructionreconstruction error: 76.3 -> 76.5 PCKNo clear effect

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