AI Paper Atlas

Research map / 3D vision / Human pose estimation

U-COPE: Taking a Further Step to Universal 9D Category-level Object Pose Estimation

li zhang, Weiqing Meng, Yan Zhong, Bin Kong, Mingliang Xu, Jianming Du, Xue Wang, Rujing Wang, Liu Liu

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
increase the number of sampled point pairs from 5,000 to 40,000 (ablation)U-COPE · ArtImage Eyeglasses3D IoU (%), part 1: 59.3 -> 66.7 (inference time 1.8 s -> 2.6 s)Improved
use 20,000 point pairs rather than 40,000 (ablation)U-COPE · ArtImage Eyeglasses3D IoU (%), part 1: 65.4 -> 66.7 for 2.1 s -> 2.6 sNo clear effect
add joint and part awareness filtering of joint points and point pairs (ablation)U-COPE · ArtImage Eyeglasses3D IoU (%), part 1: 62.9 -> 65.4Improved
add joint and part awareness filtering (ablation)U-COPE · ArtImage Eyeglassestranslation error (m), part 1: 0.058 -> 0.043Improved
use U-COPE voting framework instead of two-stage A-NCSHarticulated object pose estimation · ArtImage Drawerinference time (s): 16.5 -> 1.7Improved
use U-COPE instead of IST-Net on rigid objectsrigid object pose estimation · CAMERA25 test (3D75, 5deg)mAP: 55.6 -> 57.3Improved

Later papers that compared with this method

1 later accepted paper reports U-COPE 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