AI Paper Atlas

Research map / 3D vision / Human pose estimation

SCAPE: A Simple and Strong Category-Agnostic Pose Estimator

Yujia Liang, Zixuan Ye, Wenze Liu, Hao Lu

ECCV 2024 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 7 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
replace explicit similarity-map matching with implicit attention matching and direct coordinate regression (ablation)SCAPE (w/o GKP, KAR) · MP-100 1-shot split1PCK: 86.3 -> 89.1Improved
replace DETR decoder with full self-attention encoder (ablation)SCAPE · MP-100 1-shot split1PCK: 88.6 -> 89.1Improved
unshare Q/K projection weights between keypoints and query image (ablation)SCAPE · MP-100 1-shot split1PCK: 89.1 -> 89.8Improved
add Global Keypoint feature Perceptor (GKP) (ablation)SCAPE · MP-100 1-shot split1PCK: 89.8 -> 90.8Improved
add Keypoint Attention Refiner (KAR) (ablation)SCAPE · MP-100 1-shot split1PCK: 89.8 -> 91.2Improved
use 4 attention filters instead of 1 in KAR (ablation)KAR · MP-100 1-shot split1PCK: 90.5 -> 91.2Improved
increase hidden dimension of a single attention filter to match parameters (ablation)KAR · MP-100 1-shot split1PCK: 90.5 -> 90.3Hurt
use 2 GKP + 4 interactor layers instead of all 6 interactor (ablation)SCAPE · MP-100 1-shot split1PCK: 91.2 -> 91.6Improved
add support image into the feature interaction stage (ablation)SCAPE without GKP · MP-100 1-shot split1PCK: 89.8 -> 89.3Hurt
use DINOv2 ViT-B backbone instead of ResNet-50SCAPE · MP-100 1-shot meanPCK: 87.55 -> 91.95Improved
apply GKP and KAR to CapeFormerCapeFormer · MP-100 split1PCK: +1.1 PCKImproved
use generalist models (Painter) instead of CAPE-specific modelMP-100 keypoint localization · MP-100 split1PCK: 91.6 -> 23.9Hurt

Later papers that compared with this method

3 later accepted papers report SCAPE as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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