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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use Patch-PnP instead of PointNet-like PnP (ablation) | GDRN · LM | MEAN: 63.1 -> 71.0 | Improved |
| use Patch-PnP instead of BPnP (ablation) | GDRN · LM | MEAN: 70.6 -> 71.0 | Improved |
| use 6D rotation representation instead of quaternion (ablation) | GDRN · LM | MEAN: 57.9 -> 71.0 | Improved |
| use scale-invariant translation SITE instead of direct translation (ablation) | GDRN · LM | MEAN: 68.7 -> 71.0 | Improved |
| use disentangled L_Pose instead of point-matching loss (ablation) | GDRN · LM | MEAN: 65.9 -> 71.0 | Improved |
| add geometric supervision L_Geom (ablation) | GDRN · LM | MEAN: 63.7 -> 71.0 | Improved |
| add M_2D guidance (ablation) | GDRN · LM | MEAN: 51.0 -> 63.7 | Improved |
| add symmetry-aware rotation loss (ablation) | GDRN · LM | MEAN: 71.0 -> 70.8 | No clear effect |
| replace Faster RCNN detector with YOLOX (ablation) | GDRN · LM-O BOP | AR_BOP: 60.0 -> 61.8 | Improved |
| replace ResNet-34 with ConvNeXt-base backbone (ablation) | GDRN · LM-O BOP | AR_BOP: 62.1 -> 66.1 | Improved |
| add amodal mask prediction (ablation) | GDRN · LM-O BOP | AR_BOP: 66.1 -> 67.8 | Improved |
| add class-aware geometric head (ablation) | GDRN · LM-O BOP | AR_BOP: 67.8 -> 68.6 | Improved |
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.
- HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation (ICCV 2025 · better on 1 of 1 shared result)
- Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimation (TPAMI 2025 · better on 1 of 1 shared result)
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.
- ZebraPose — ZebraPose: Coarse To Fine Surface Encoding for 6DoF Object Pose Estimation (CVPR 2022) · better on 2 of 2 shared results
- FoundationPose — FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects (CVPR 2024) · better on 1 of 1 shared result
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
- GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation (CVPR 2021 · similarity 0.94)
- Segmentation-Driven 6D Object Pose Estimation (CVPR 2019 · similarity 0.91)
- GPV-Pose: Category-Level Object Pose Estimation via Geometry-Guided Point-Wise Voting (CVPR 2022 · similarity 0.91)
- Single-Stage 6D Object Pose Estimation (CVPR 2020 · similarity 0.91)
- DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-Scale Consistency (CVPR 2021 · similarity 0.90)
- Pose without Guesses: Generalizable Object Pose Estimation From a Single Reference (IJCV 2026 · similarity 0.89)
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.
