AI Paper Atlas

Research map / 3D vision / Human pose estimation

GDRNPP: A Geometry-Guided and Fully Learning-Based Object Pose Estimator

Xingyu Liu, Ruida Zhang, Chenyangguang Zhang, Gu Wang, Jiwen Tang, Zhigang Li, Xiangyang Ji

TPAMI 2025 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 56 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
use Patch-PnP instead of PointNet-like PnP (ablation)GDRN · LMMEAN: 63.1 -> 71.0Improved
use Patch-PnP instead of BPnP (ablation)GDRN · LMMEAN: 70.6 -> 71.0Improved
use 6D rotation representation instead of quaternion (ablation)GDRN · LMMEAN: 57.9 -> 71.0Improved
use scale-invariant translation SITE instead of direct translation (ablation)GDRN · LMMEAN: 68.7 -> 71.0Improved
use disentangled L_Pose instead of point-matching loss (ablation)GDRN · LMMEAN: 65.9 -> 71.0Improved
add geometric supervision L_Geom (ablation)GDRN · LMMEAN: 63.7 -> 71.0Improved
add M_2D guidance (ablation)GDRN · LMMEAN: 51.0 -> 63.7Improved
add symmetry-aware rotation loss (ablation)GDRN · LMMEAN: 71.0 -> 70.8No clear effect
replace Faster RCNN detector with YOLOX (ablation)GDRN · LM-O BOPAR_BOP: 60.0 -> 61.8Improved
replace ResNet-34 with ConvNeXt-base backbone (ablation)GDRN · LM-O BOPAR_BOP: 62.1 -> 66.1Improved
add amodal mask prediction (ablation)GDRN · LM-O BOPAR_BOP: 66.1 -> 67.8Improved
add class-aware geometric head (ablation)GDRN · LM-O BOPAR_BOP: 67.8 -> 68.6Improved

Later papers that compared with this method

2 later accepted papers report GDRNPP as a baseline in their results tables; 2 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 2 of 2 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