AI Paper Atlas

Research map / 3D vision / Human pose estimation

EdgeCape: Edge Weight Prediction For Category-Agnostic Pose Estimation

Or Hirschorn, Shai Avidan

ICLR 2026 · 3D vision › Human pose estimation · approach: Learned camera pose estimation

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 pose-graph prediction (predicted weighted edges) to GraphCape (ablation)GraphCape · MP-100 split 1, 1-shotmPCK: 79.87 -> 80.76Improved
add Markov Attention Bias to GraphCape (ablation)GraphCape · MP-100 split 1, 1-shotmPCK: 79.87 -> 80.78Improved
combine pose-graph prediction with Markov Attention Bias (ablation)EdgeCape · MP-100 split 1, 1-shotmPCK: 79.87 -> 81.96Improved
predict weighted pose-graphs instead of using fixed unweighted graphGraphCape · MP-100 1-shot averagemPCK: 75.73 -> 77.72Improved
predict weighted pose-graphs instead of using fixed unweighted graph (PCK@0.2, saturated)GraphCape · MP-100 5-shot averagePCK@0.2: 91.50 -> 91.87Improved
supervise adjacency with decoder-based masking instead of auxiliary GCN reconstruction (ablation)EdgeCape · MP-100 split 1, 1-shotPCK@0.2: 92.88 -> 93.57Improved
predict graph from keypoint features only instead of keypoint plus full image features (ablation)pose-graph predictor · MP-100 split 1, 1-shotPCK: -0.24%Hurt
use MLP or multi-head attention edge predictors instead of cosine similarity (ablation)pose-graph predictor · MP-100PCKNo clear effect
use DINOv2 instead of SwinV2 backbone (ablation)EdgeCape · MP-100 split 1, 1-shotmPCK: 80.63 -> 81.96Improved
inject up to 16 random noisy edges in input graph (ablation)EdgeCape vs GraphCape · MP-100 noisy prior graphPCKImproved
use EdgeCape instead of GraphCape in super cross-category settingEdgeCape · MP-100 super cross-categoryPCK@0.2: Human Body 88.38 -> 91.38; Vehicle 44.06 -> 44.12; Furniture 45.56 -> 54.03Mixed
use fully-connected prior graph (no topology info) (ablation)GraphCape · MP-100PCKHurt

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