AI Paper Atlas

Research map / 3D vision / Human pose estimation

Towards Robust and Expressive Whole-body Human Pose and Shape Estimation

Hui En Pang, Zhongang Cai, Lei Yang, Qingyi Tao, Zhonghua Wu, Tianwei Zhang, Ziwei Liu

NeurIPS 2023 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 7 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 all location features (ablation)Base (DR54) hand model · FreiHANDPA-PVE: 7.67 -> 7.46Improved
add strong augmentation (ablation)HMR hand model · FreiHANDPA-PVE: 7.85 -> 8.11Hurt
add contrastive loss and positive samples (ablation)LF (all) hand model · FreiHANDPVE: 15.59 -> 14.57Improved
add projected segmentation loss (ablation)LF (all) hand model with part segmentation supervision · FreiHANDMPJPE: 14.92 -> 14.38Improved
add all location features (ablation)HMR body model · 3DPW testMPJPE: 96.2 -> 105.7Hurt
use keypoints rather than pose rotations as the contrastive representation, with positive samples (ablation)RoboSMPLX body model · 3DPW testPA-MPJPE: 55.9 -> 55.4Improved
use pose plus global orientation as the contrastive representation (ablation)RoboSMPLX body model · 3DPW testPA-MPJPE: 55.9 -> 76.8Hurt
use pose-variant augmentation to form positive samples (ablation)contrastive hand model · FreiHANDPA-PVE: 7.67 -> 8.15Hurt
use color and location augmentations for positive samples (ablation)contrastive hand model · FreiHANDPVE: 16.08 -> 14.77Improved
add contrastive learning to strong augmentation (ablation)HMR hand model · FreiHANDPA-PVE: 8.11 -> 7.41Improved
use RoboSMPLX instead of Hand4Wholewhole-body hand estimation · FreiHAND positional augmentationsPVE under Transy +0.2y: 22.51 -> 15.50Improved
use RoboSMPLX instead of ExPosewhole-body face estimation · EHF positional augmentations3DRMSE under Transy +0.2y: 2.46 -> 2.13Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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