AI Paper Atlas

Research map / 3D vision / Human pose estimation

Faster VoxelPose: Real-Time 3D Human Pose Estimation by Orthographic Projection

Hang Ye, Wentao Zhu, Chunyu Wang, Rujie Wu, Yizhou Wang

ECCV 2022 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 70 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 person-specific feature masking (ablation)Faster VoxelPose · CMU PanopticMPJPE: 21.07mm -> 18.26mmImproved
add person-specific feature masking (ablation)Faster VoxelPose · CMU PanopticAP25: 72.05 -> 85.22Improved
add adaptive weighted fusion instead of mean (ablation)Faster VoxelPose · CMU PanopticMPJPE: 20.11mm -> 18.26mmImproved
add adaptive weighted fusion instead of mean (ablation)Faster VoxelPose · CMU PanopticAP25: 77.23 -> 85.22Improved
increase cameras from 4 to 5 (ablation)Faster VoxelPose · CMU PanopticMPJPE: 21.12mm -> 18.26mmImproved
increase cameras from 3 to 5 (ablation)Faster VoxelPose · CMU PanopticMPJPE: 26.13mm -> 18.26mmImproved
use finer JLN voxels 64^3 instead of 48^3 (ablation)Faster VoxelPose · CMU PanopticMPJPE: 19.66mm -> 18.26mmImproved
use finer JLN voxels 64^3 instead of 32^3 (ablation)Faster VoxelPose · CMU PanopticMACs: 2.167G -> 8.670G MACs; MPJPE 20.47mm -> 18.26mmMixed
replace 3D-CNN VoxelPose with orthographic projection and 2D-CNNFaster VoxelPose · CMU Panopticinference time: 316.0ms -> 32.2msImproved
replace 3D-CNN VoxelPose with orthographic projection and 2D-CNNFaster VoxelPose · CMU PanopticMPJPE: 17.68mm -> 18.26mmHurt
replace VoxelPose with Faster VoxelPoseFaster VoxelPose · Shelfaverage PCP3D: 97.0 -> 97.6Improved
replace VoxelPose with Faster VoxelPoseFaster VoxelPose · Campusaverage PCP3D: 96.7 -> 96.2Hurt

Later papers that compared with this method

3 later accepted papers report Faster VoxelPose as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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