AI Paper Atlas

Research map / 3D vision / Human pose estimation

Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation

Yangzheng Wu, Michael Alan Greenspan

ECCV 2024 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 5 citations (OpenAlex)

Read the paper

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
use dense multi-layer feature matching in the Adapter instead of sparse matching of the radial map only (ablation)RKHSPose · LM + five BOP core datasetsAR: 77.9 -> 84.4Improved
alternate real and synthetic epochs instead of sequential training (ablation)RKHSPose · LM + five BOP core datasetsAR: 81.9 -> 84.4Improved
add trainable weights to the linear kernel (ablation)RKHS Adapter · LM + five BOP core datasetsAR: 71.0 -> 84.4Improved
use RBF kernel instead of linear kernel (both with trainable weights) (ablation)RKHS Adapter · LM + five BOP core datasetsAR: 84.4 -> 81.6Hurt
use MMD instead of KL divergence as domain gap loss (ablation)RKHS Adapter · LM + five BOP core datasetsAR: 77.9 -> 84.4Improved
use MMD instead of Wasserstein distance (ablation)RKHS Adapter · LM + five BOP core datasetsAR: 80.8 -> 84.4Improved
add unlabeled real images with pseudo-keypoint adapter training to synthetic-only training (ablation)RKHSPose · LINEMODADD(S): 78.2 -> 95.8Improved
increase number of real images beyond 160-320 (ablation)RKHSPose · BOP datasetsAR: +0.1%No clear effect
add ICP refinement (ablation)RKHSPose · YCB-VideoADD(S) AUC: 82.8 -> 83.0Improved
use RKHSPose without real GT labels versus fully supervised methodsBOP Occlusion LINEMOD · Occlusion LINEMODADD(S): 68.2 vs 79.7 (RADet+PFA)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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