AI Paper Atlas

Research map / 3D vision / Human pose estimation

E-3DPSM: A State Machine for Event-based Egocentric 3D Human Pose Estimation

Mayur Deshmukh, Hiroyasu Akada, Helge Rhodin, Christian Theobalt, Vladislav Golyanik

CVPR 2026 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 0 citations (OpenAlex)

Read the paper

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 SSM blocks to the spatiotemporal encoder (ablation)E-3DPSM · EE3D-RMPJPE: 118.53 -> 84.45Improved
add SSM blocks at all stages instead of only stage four (ablation)E-3DPSM · EE3D-RMPJPE: 90.18 -> 84.45Improved
add deformable attention (ablation)E-3DPSM · EE3D-RMPJPE: 88.27 -> 84.45Improved
add learned Kalman-style fusion of delta and direct poses (ablation)E-3DPSM · EE3D-RMPJPE: 141.22 -> 84.45Improved
add delta-pose regression alongside direct pose (ablation)E-3DPSM · EE3D-Re_smooth: 17.22 -> 8.40Improved
make Kalman fusion learnable instead of static (ablation)E-3DPSM · EE3D-RMPJPE: 88.31 -> 84.45Improved
use globally learned Q and R instead of input/state-dependent (ablation)E-3DPSM · EE3D-RMPJPE: 91.15 -> 84.45Improved
train non-causally (bidirectional) instead of forward-only (ablation)E-3DPSM · EE3D-RMPJPE: 89.88 -> 84.45Improved
increase training sequence length from 20 to 40 poses (ablation)E-3DPSM · EE3D-RMPJPE: 86.25 -> 84.45Improved
reset SSM states every 40 frames at inference (ablation)E-3DPSM · EE3D-RMPJPE: 84.45 -> 104.56Hurt
reset fusion states every 40 frames at inference (ablation)E-3DPSM · EE3D-Re_smooth: 8.40 -> 21.50Hurt
use fixed LNES instead of learned voxel-based representation (ablation)E-3DPSM · EE3D-RMPJPE: 100.25 -> 84.45Improved

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