AI Paper Atlas

Research map / 3D vision / Human pose estimation

GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation

Jiyong Rao, Yu Wang, Shengjie Zhao

ICLR 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 KL regularization on posterior (ablation)GenCape-T · MP-100 Split-1 1-shotPCK@0.2: 91.19 -> 91.43Improved
add sparsity loss on top of KL (ablation)GenCape-T · MP-100 Split-1 1-shotPCK@0.2: 91.43 -> 91.75Improved
add Compositional Graph Transfer (ablation)GenCape-T · MP-100 Split-1 1-shotPCK@0.2: 91.75 -> 92.05Improved
use iterative layer-wise structure refinement (ablation)GenCape-T · MP-100 Split-1 1-shotPCK@0.2: 91.48 -> 92.05Improved
use learned adjacency instead of self-attention weights (ablation)GenCape-T · MP-100 Split-1 1-shotPCK@0.2: 89.33 -> 92.05Improved
use learned graph rather than random initialized graph (ablation)GenCape-T · MP-100 Split-1 1-shotPCK@0.2: 84.39 -> 92.05Improved
impose symmetry on learned adjacency (ablation)GenCape-T · MP-100 Split-1 1-shotPCK@0.2: 91.71 -> 92.05Improved
query weighting across layers plus Bayesian fusion across samples vs same strategy at both (ablation)GenCape-T · MP-100 Split-1 1-shotPCK@0.2: 91.74 -> 92.05Improved
increase latent dimension from 32 to 128 (ablation)GenCape-T · MP-100 Split-1 1-shotPCK@0.2: 92.05 -> 91.40Hurt
use 3 posterior samples rather than 2 or 5 (ablation)GenCape-T · MP-100 Split-1 1-shotPCK@0.2: 91.60 / 91.63 -> 92.05Improved
use GenCape instead of GraphCape for cross-supercategory transferGenCape · Cross super-category / Furniture->HumanBodyPCK@0.2: Felidae->Person 56.26 -> 68.08; Furniture->HumanBody 73.79 -> 73.09Mixed
use GenCape on 1-shot MP-100 instead of GraphCapeGenCape-T · MP-100 1-shot avgPCK@0.2: 87.23 -> 88.09Improved

Later papers that compared with this method

1 later accepted paper reports GenCape as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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