AI Paper Atlas

Research map / 3D vision / Human pose estimation

Scene-Aware Egocentric 3D Human Pose Estimation

Jian Wang, Diogo Luvizon, Weipeng Xu, Lingjie Liu, Kripasindhu Sarkar, Christian Theobalt

CVPR 2023 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 58 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 scene-aware voxel features and scene geometry to egocentric pose estimationEgoPW-style egocentric pose estimation · Our test datasetMPJPE: 189.6 -> 118.5Improved
Add scene-aware voxel features and scene geometry to egocentric pose estimationEgoPW-style egocentric pose estimation · Wang et al. test datasetPA-MPJPE: 81.71 -> 76.50Improved
Add scene-aware voxel features and scene geometry to egocentric pose estimationEgoPW-style egocentric pose estimation · Mo²Cap² test datasetPA-MPJPE: 83.17 -> 79.65Improved
Add scene-aware voxel features and scene geometry to egocentric pose estimationEgoPW-style egocentric pose estimation · Our test datasetContact: 38.8% -> 89.4%Improved
Add scene depth input to the V2V pose network (ablation)Scene-aware egocentric pose estimator · Our test datasetMPJPE: 188.1 -> 118.5Improved
Use depth inpainting to recover scene depth behind the human body (ablation)Scene-aware egocentric pose estimator · Our test datasetMPJPE: 124.2 -> 118.5Improved
Use depth inpainting to recover scene depth behind the human body (ablation)Scene depth estimator · Our test datasetAbs-Rel: 0.3834 -> 0.1069Improved
Use ground-truth scene depth instead of estimated depth (ablation)Scene-aware egocentric pose estimator · Our test datasetMPJPE: 118.5 -> 109.9Improved
Represent image pose features and scene depth jointly in voxel space rather than simple concatenation (ablation)Egocentric pose estimation · Our test datasetMPJPE: 149.6 -> 118.5Improved
Add a scene-contact optimization term to EgoPW predictions (ablation)EgoPW · Our test datasetMPJPE: 187.1 vs 189.6No clear effect

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