无需训练的单目6D位姿估计，通过几何感知加权提升稳定性。
GNC-Pose: Geometry-Aware GNC-PnP for Accurate 6D Pose Estimation
- 基于渲染初始化与几何一致性加权，构建鲁棒对应关系。
- 在YCB数据集上达到与学习方法相当的精度，误差低于1.5°/0.02m。
- 适合无标注数据场景，可直接部署于真实工业环境。
我们提出GNC-Pose，一种完全无需学习的单目6D物体位姿估计流程，适用于有纹理物体。该方法从特征匹配与渲染对齐得到的粗略2D-3D对应关系出发，基于渐进非凸（GNC）优化原理，引入一种基于聚类的几何感知加权机制，根据模型的3D结构一致性为每个点分配稳健的置信度。该几何先验与加权策略显著提升了在严重异常值干扰下的优化稳定性。最后通过莱文伯格-马尔夸特（LM）精修进一步提高精度。我们在YCB物体与模型集上测试了该方法，尽管不依赖任何学习特征、训练数据或类别特定先验，其性能仍可与基于学习和非学习方法相媲美，为无学习的6D位姿估计提供了一种简单、鲁棒且实用的解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。