Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.06565 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915964981870592 |
|---|---|
| author | Liu, Xiujin |
| author_facet | Liu, Xiujin |
| contents | We present GNC-Pose, a fully learning-free monocular 6D object pose estimation pipeline for textured objects that combines rendering-based initialization, geometry-aware correspondence weighting, and robust GNC optimization. Starting from coarse 2D-3D correspondences obtained through feature matching and rendering-based alignment, our method builds upon the Graduated Non-Convexity (GNC) principle and introduces a geometry-aware, cluster-based weighting mechanism that assigns robust per point confidence based on the 3D structural consistency of the model. This geometric prior and weighting strategy significantly stabilizes the optimization under severe outlier contamination. A final LM refinement further improve accuracy. We tested GNC-Pose on The YCB Object and Model Set, despite requiring no learned features, training data, or category-specific priors, GNC-Pose achieves competitive accuracy compared with both learning-based and learning-free methods, and offers a simple, robust, and practical solution for learning-free 6D pose estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06565 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GNC-Pose: Geometry-Aware GNC-PnP for Accurate 6D Pose Estimation Liu, Xiujin Computer Vision and Pattern Recognition We present GNC-Pose, a fully learning-free monocular 6D object pose estimation pipeline for textured objects that combines rendering-based initialization, geometry-aware correspondence weighting, and robust GNC optimization. Starting from coarse 2D-3D correspondences obtained through feature matching and rendering-based alignment, our method builds upon the Graduated Non-Convexity (GNC) principle and introduces a geometry-aware, cluster-based weighting mechanism that assigns robust per point confidence based on the 3D structural consistency of the model. This geometric prior and weighting strategy significantly stabilizes the optimization under severe outlier contamination. A final LM refinement further improve accuracy. We tested GNC-Pose on The YCB Object and Model Set, despite requiring no learned features, training data, or category-specific priors, GNC-Pose achieves competitive accuracy compared with both learning-based and learning-free methods, and offers a simple, robust, and practical solution for learning-free 6D pose estimation. |
| title | GNC-Pose: Geometry-Aware GNC-PnP for Accurate 6D Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.06565 |