AI Paper Atlas

Research map / 3D vision / Human pose estimation

EvHandPose: Event-Based 3D Hand Pose Estimation With Sparse Supervision

Jianping Jiang, Jiahe Li, Baowen Zhang, Xiaoming Deng, Boxin Shi

TPAMI 2024 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 28 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 hand flow representation (ablation)EvHandPose · Strong light, fixed poses3D-MPJPE: 40.30 -> 28.98Improved
hand flow instead of ECI (ablation)EvHandPose · Strong light, fixed poses3D-MPJPE: 32.16 -> 28.98Improved
hand flow instead of Matrix-LSTM (ablation)EvHandPose · Normal scenes, fixed poses3D-MPJPE: 58.36 -> 19.82Improved
add weak-supervision losses over fully supervised (ablation)EvHandPose · Normal scenes, fixed poses3D-MPJPE: 22.76 -> 19.82Improved
add hand-edge loss (ablation)EvHandPose · Flash scenes, fixed poses3D-MPJPE: 33.52 -> 32.80Improved
add CM loss (ablation)EvHandPose · Flash scenes, fixed poses3D-MPJPE: 36.42 -> 32.80Improved
add hand-edge loss (ablation)EvHandPose · Fast motion, random poses2D-MPJPE: 9.00 -> 8.18Hurt
add hand-edge loss (ablation)EvHandPose · Strong light, fixed poses3D-MPJPE: 29.13 -> 28.98No clear effect
train on real EvRealHands instead of EventHands synthetic data (ablation)EvHandPose · Normal scenes, fixed poses3D-MPJPE: 70.13 -> 19.82Improved
train on real EvRealHands instead of InterHand2.6M synthetic events (ablation)EvHandPose · Normal scenes, fixed poses3D-MPJPE: 51.01 -> 19.82Improved
EvHandPose events instead of RGB MobRecon under strong lightEvHandPose · Strong light, fixed poses3D-MPJPE: 40.54 -> 28.98Improved
EvHandPose events instead of RGB MobRecon in normal scenesEvHandPose · Normal scenes, fixed poses3D-MPJPE: 19.28 -> 19.82No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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