AI Paper Atlas

Research map / 3D vision / Human pose estimation

Diffusion-based Personalized Pathology Disentanglement for Impaired Gait Analysis

Xiaoyue Wan, Xu Zhao

AAAI 2026 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 0 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
adapt MotionBERT to 3D pose input and pretrain on 3D data (ablation)MotionBERT baseline · PDGaitaccuracy: 0.42 -> 0.52Improved
finetune 3DmotionBERT on PDGait/3DGait (ablation)3DmotionBERT · PDGaitaccuracy: 0.52 -> 0.56Improved
add Gait Denoiser residual (pathology disentanglement) (ablation)3DmotionBERT · PDGaitaccuracy: 0.56 -> 0.68Improved
add Dual Pathology Disentanglement with temporal alignment (ablation)DPPD · PDGaitaccuracy: 0.68 -> 0.73Improved
use pathological residual features instead of raw features (ablation)DPPD · PDGait subsetaccuracy: 0.53 -> 0.68Improved
personalize normal gait using same-subject memory bank vs other subjects (ablation)normal gait reference · PDGait subsetaccuracy: 0.57 -> 0.81Improved
add personality contrastive loss to GD (ablation)DPPD GD · PDGait subsetaccuracy: 0.64 -> 0.68Improved
add personality contrastive loss to GD (ablation)DPPD GD · PDGait subsetprecision: 0.66 -> 0.66No clear effect
add DTW temporal alignment (ablation)DPPD · PDGaitpathology magnitude vs severity trendImproved
add temporal consistency loss (ablation)3DmotionBERT · PDGaitseparability of motion pathologyImproved
DPPD versus GaitCLIP on 3DGait dementia subtypingDPPD · 3DGaitaccuracy: 0.90 -> 0.91Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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