AI Paper Atlas

Research map / 3D vision / Human pose estimation

Occlusion-Resilient Category-Agnostic Pose Estimation with Conditional Flow Matching

Jiyong Rao, Shengjie Zhao, Yu Wang, Hao Deng

ECCV 2026 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 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
add heatmap-guided initialization over center (query-centered, 30 steps) initialization (ablation)FlowCape · Occ80 Split 1PCK@0.2: 84.77 -> 86.72Improved
add confidence weighting to heatmap-guided initialization (ablation)FlowCape · Occ80 Split 1PCK@0.2: 86.72 -> 86.71No clear effect
run 30 ODE steps instead of 20 for center-initialized flow (ablation)FlowCape · Occ80 Split 1PCK@0.2: 83.13 -> 84.77Improved
add H-Init, flow matching losses and auxiliary losses on top of ODE-only (ablation)FlowCape · Occ80 Split 1PCK@0.2: 72.81 -> 86.72Improved
add Lrfm and Lflow flow-matching supervision (ablation)FlowCape · Occ80 Split 1PCK@0.2: +0.9%Improved
use full FlowCape instead of CapeX baseline (ablation)FlowCape · Occ80 Split 1 (SwinV2-Tiny)PCK@0.2: 85.68 -> 86.72Improved
increase pose head depth from 1 to 3 layers (ablation)Riemannian Pose Head · Occ80 Split 1PCK@0.2: 83.51 -> 86.72Improved
increase pose head depth from 3 to 4 layers (ablation)Riemannian Pose Head · Occ80 Split 1PCK@0.2: 86.72 -> 84.96Hurt
increase hidden dimension from 256 to 384 (ablation)Riemannian Pose Head · Occ80 Split 1PCK@0.2: 86.72 -> 86.77No clear effect
increase hidden dimension from 128 to 256 (ablation)Riemannian Pose Head · Occ80 Split 1PCK@0.2: 85.61 -> 86.72Improved
lower lambda_traj from 1.0 to 10^-3 (ablation)FlowCape · Occ80 Split 1PCK@0.2: 86.72 -> 84.79Hurt
use FlowCape instead of CapeX with SwinV2-SmallFlowCape · Occ80 (avg of S1-S3)PCK@0.2: 88.07 -> 89.12Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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