AI Paper Atlas

Research map / 3D vision / Human pose estimation

COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation

Yuchen Che, Jingtu Wu, Hao Zheng, Asako Kanezaki

CVPR 2026 · 3D vision › Human pose estimation · approach: Learned camera 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
replace argmax with confidence-marginal OT correspondence (ablation)COG · YCB-Vmean mAP: 71.4 -> 74.3Improved
replace softmax with confidence-marginal OT correspondence (ablation)COG · YCB-Vmean mAP: 71.5 -> 74.3Improved
use confidence marginals instead of uniform marginals in OT (ablation)COG · YCB-Vmean mAP: 75.2 -> 75.9Improved
add semantic loss L_sem (confidence OT, no cycle loss) (ablation)COG · YCB-Vmean mAP: 74.3 -> 75.6Improved
add cycle loss L_cycl (confidence OT, no sem loss) (ablation)COG · YCB-Vmean mAP: 74.3 -> 74.4No clear effect
add both L_sem and L_cycl (argmax correspondence) (ablation)COG argmax · YCB-Vmean mAP: 71.4 -> 73.1Improved
add L_sem alone with argmax correspondence (ablation)COG argmax · YCB-Vmean mAP: 71.4 -> 70.5Hurt
add semantic priors to the affinity kernel (ablation)COG (2 Sinkhorn iters) · YCB-VmAP: 73.2 -> 75.9Improved
increase Sinkhorn iterations from 2 to 8 (with semantic priors) (ablation)COG · YCB-VmAP: 75.9 -> 75.7Hurt
add one refinement iteration at inference (ablation)COG · BOP benchmarksmean mAP: over 1%Improved
use COG with 1% training data instead of DINO+PHS (ablation)COG · BOP meanmAP: 28.7 -> 64.5Improved
train on 100% instead of 5% of the data (ablation)COG · BOP meanmAP: 67.3 -> 68.8Improved

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