AI Paper Atlas

Research map / 3D vision / Human pose estimation

Event6D: Event-based Novel Object 6D Pose Tracking

Jae-Young Kang, Hoonhee Cho, Taeyeop Lee, Minjun Kang, Bowen Wen, Youngho Kim, Kuk-Jin Yoon

CVPR 2026 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 2 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 depth reconstruction (ablation)EventTrack6D baseline · Event6D (120 FPS eval, mean over objects)ADD-S AUC: 18.45 -> 28.67Improved
add image reconstruction (ablation)EventTrack6D baseline · Event6D (120 FPS eval, mean over objects)ADD-S AUC: 18.45 -> 30.53Improved
add image reconstruction to depth recon (ablation)EventTrack6D · Event6D (120 FPS eval, mean over objects)ADD-S AUC: 28.67 -> 52.79Improved
add depth reconstruction to image recon (ablation)EventTrack6D · Event6D (120 FPS eval, mean over objects)ADD-S AUC: 30.53 -> 52.79Improved
add motion vector to depth reconstruction (ablation)EventTrack6D depth module · Event6D (120 FPS eval, mean over objects)ADD-S AUC: 41.88 -> 52.79Improved
add image feature to depth reconstruction (ablation)EventTrack6D depth module · Event6D (120 FPS eval, mean over objects)ADD-S AUC: 42.26 -> 52.79Improved
add both motion vector and image feature to depth recon (ablation)EventTrack6D depth module · Event6D (120 FPS eval, mean over objects)ADD-S AUC: 36.03 -> 52.79Improved
fine-tune FoundationPose on event inputs vs adding reconstructionFoundationPose · Event6D (120 FPS eval, mean over objects)ADD-S AUC: 22.93 -> 52.79Improved
EventTrack6D vs RGB-D baselines at 30 FPSEventTrack6D · Event6D (30 FPS eval, mean over objects)ADD-S AUC: 16.63 -> 56.08Improved
EventTrack6D vs E2VID+FoundationPose on EventHO3DEventTrack6D · EventHO3D (30 FPS eval, mean)ADD-S AUC: 57.10 -> 64.75Improved

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