AI Paper Atlas

Research map / 3D vision / Human pose estimation

From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras

Youngho Kim, Hoonhee Cho, Kuk-Jin Yoon

ICCV 2025 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 5 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 motion-aware event-based blur augmentation (MBA) (ablation)Baseline student · EHPT-XC target blurmAP: 37.5 -> 40.4Improved
add Stage 2 pseudo-label training (ablation)Baseline student · EHPT-XC target blurmAP: 37.5 -> 49.1Improved
add MBA on top of Stage 2 (ablation)Ours · EHPT-XC target blurmAP: 49.1 -> 50.4Improved
add Stages 3 and 4 refinement (ablation)Ours · EHPT-XC target blurmAP: 50.4 -> 51.6Improved
add motion augmentation (ablation)Stage 1 teacher · EHPT-XC target blurmAP: 46.5 -> 46.7Improved
add blur translation to motion augmentation (ablation)Stage 1 teacher · EHPT-XC target blurmAP: 46.7 -> 46.9Improved
combine image+event and event sub-teachers with refinement (ablation)Stage 1 teacher · EHPT-XC target blurmAP: 43.5 -> 46.9Improved
add refinement module to a single sub-teacher (ablation)Stage 1 teacher · EHPT-XC target blurmAP: 40.4 -> 39.6No clear effect
use refinement network instead of mean heatmap (ablation)Stage 1 teacher · EHPT-XC target blurmAP: 45.4 -> 46.9Improved
use refinement network instead of spatial attention (ablation)Stage 1 teacher · EHPT-XC target blurmAP: 41.9 -> 46.9Improved
set Stage 2 mask threshold th to 0.1 instead of 0.3 (ablation)Ours · EHPT-XC target blurmAP: 45.7 -> 50.4Improved
set Stage 4 mask threshold th' to 0.1 instead of 0.05 (ablation)Ours · EHPT-XC target blurmAP: 49.7 -> 51.6Improved

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